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

    Neuronpedia

    INDEX
    Explanations

    conditional statements and hypothetical situations

    oai_token-act-pair · gpt-3.5-turbo

    conditional statements or phrases implying potential outcomes or consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vez
    -0.68
    âĺ
    -0.63
    standing
    -0.59
     Chemistry
    -0.59
    ESSION
    -0.58
    Bus
    -0.57
    said
    -0.57
    has
    -0.56
    MENTS
    -0.56
     Corpus
    -0.56
    POSITIVE LOGITS
     otherwise
    1.04
     underpin
    0.94
     propel
    0.94
    rouse
    0.93
     culmin
    0.92
     someday
    0.91
     allow
    0.91
     enable
    0.88
     preclude
    0.87
     detriment
    0.86
    Act Density 0.172%

    No Known Activations