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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating certainty or strong belief

    oai_token-act-pair · gpt-3.5-turbo

    the word "certainly" used to express conviction or emphasis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    entary
    -0.82
    idas
    -0.81
    ingly
    -0.79
    ENCY
    -0.78
    glers
    -0.71
    ENC
    -0.70
    awaru
    -0.70
    ULAR
    -0.70
    roups
    -0.69
    locking
    -0.68
    POSITIVE LOGITS
     deserved
    0.77
     qualifies
    0.76
     suited
    0.73
     wasn
    0.73
     wouldn
    0.72
     weren
    0.70
     influenced
    0.70
     ought
    0.69
     not
    0.67
     behaved
    0.67
    Act Density 0.054%

    No Known Activations