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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing strong emotions or opinions

    oai_token-act-pair · gpt-3.5-turbo

    familiar conversational phrases or expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     respectively
    -0.82
     ..."
    -0.75
     thereto
    -0.70
    .","
    -0.69
     �
    -0.68
    "],"
    -0.67
     incub
    -0.65
     ``(
    -0.63
     \"
    -0.61
     predomin
    -0.61
    POSITIVE LOGITS
    resa
    1.33
    odore
    1.26
    xiety
    1.13
    swers
    0.98
    notations
    0.93
    laughter
    0.89
    romeda
    0.88
    bye
    0.87
    chieve
    0.84
    nir
    0.79
    Act Density 0.629%

    No Known Activations