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

    Neuronpedia

    INDEX
    Explanations

    phrases and words that express confusion or dissatisfaction with situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     when
    -1.17
     in
    -1.08
     while
    -1.08
     after
    -1.07
     during
    -1.06
     with
    -1.00
     because
    -0.99
     as
    -0.96
     for
    -0.95
     at
    -0.94
    POSITIVE LOGITS
    enderror
    0.66
     ་་
    0.65
     ſind
    0.63
     estekak
    0.62
    0.61
     Baillargeon
    0.60
    VersionUID
    0.58
    ."</
    0.58
     Prologue
    0.56
    oplasty
    0.56
    Act Density 1.216%

    No Known Activations