Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    expressions of self-identity and subjective experience

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Gimme
    -0.82
     biar
    -0.69
     transfieras
    -0.65
     Tampoco
    -0.64
    Dunno
    -0.64
    כשיו
    -0.64
    multicolumn
    -0.63
    PostConstruct
    -0.63
    SupportActionBar
    -0.63
    viewDidLoad
    -0.62
    POSITIVE LOGITS
    mektedir
    0.95
    aarrggbb
    0.90
    Diweddarwch
    0.64
    非常的
    0.62
     goederen
    0.61
    AutoScaleMode
    0.60
     ontvangen
    0.59
    maktadır
    0.59
    AMAZING
    0.58
    miştir
    0.57
    Act Density 0.545%

    No Known Activations