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

    Neuronpedia

    INDEX
    Explanations

    expressions related to assumptions and misconceptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     calendriers
    -0.68
    writeFieldEnd
    -0.59
    __':
    -0.58
    (--
    -0.54
    DockStyle
    -0.54
    godic
    -0.54
     neceff
    -0.53
    issued
    -0.53
    StateToProps
    -0.52
    Припев
    -0.52
    POSITIVE LOGITS
    BeginContext
    0.64
     StatelessWidget
    0.60
     thought
    0.55
     conception
    0.55
     tưởng
    0.53
    ⓧ
    0.53
     Thought
    0.51
     beginning
    0.51
    WebVitals
    0.50
    存于互联网档案馆
    0.49
    Act Density 0.282%

    No Known Activations