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

    Neuronpedia

    INDEX
    Explanations

    expressions of emotional reactions and feedback

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     فريبيس
    -0.98
    UserScript
    -0.90
     незавершена
    -0.89
    /**
    -0.86
    GEBURTSDATUM
    -0.86
    UnsafeEnabled
    -0.85
     consultato
    -0.83
     StringTokenizer
    -0.81
     صوتيه
    -0.81
    sizeCache
    -0.81
    POSITIVE LOGITS
     #
    0.47
     ha
    0.45
     .
    0.44
    迫
    0.43
    !
    0.42
     
    0.41
    ↵↵
    0.41
    well
    0.41
    たの
    0.41
    ciaio
    0.40
    Act Density 0.122%

    No Known Activations