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

    Neuronpedia

    INDEX
    Explanations

    responses or answers in a conversation

    oai_token-act-pair · gpt-3.5-turbo

    instances of dialogue or responses within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    icipated
    -0.69
    dar
    -0.67
    cipled
    -0.67
    ctors
    -0.67
    bons
    -0.66
    ammy
    -0.64
    cgi
    -0.62
    hoff
    -0.62
    teenth
    -0.62
     Blazers
    -0.62
    POSITIVE LOGITS
     angrily
    1.01
     favorably
    0.93
     sarcast
    0.90
     enthusiastically
    0.86
     affirm
    0.82
     politely
    0.80
     promptly
    0.77
     thereto
    0.77
     harshly
    0.77
     indign
    0.77
    Act Density 0.039%

    No Known Activations