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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating responsibility or obligations related to actions and outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     TextAppearance
    -0.76
    MessageOf
    -0.57
    principalColumn
    -0.56
     '\\;'
    -0.56
    ItemBackground
    -0.56
    enterOuterAlt
    -0.54
    FunctionFlags
    -0.52
    ագրություններ
    -0.49
    RUnlock
    -0.49
     nakalista
    -0.48
    POSITIVE LOGITS
     before
    3.94
    before
    3.25
     antes
    3.08
     sebelum
    3.05
     Before
    2.98
    Before
    2.97
     ennen
    2.75
     BEFORE
    2.70
     قبل
    2.66
     înainte
    2.61
    Act Density 3.056%

    No Known Activations