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

    Neuronpedia

    INDEX
    Explanations

    sentences or phrases indicating agreement with statements or opinions

    oai_token-act-pair · gpt-3.5-turbo

    expressions of agreement or consensus

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gallery
    -0.71
    asus
    -0.68
    hyde
    -0.63
    sembly
    -0.61
    oufl
    -0.58
    inary
    -0.58
    hung
    -0.57
    ccording
    -0.56
     emergencies
    -0.54
    ague
    -0.54
    POSITIVE LOGITS
     vehemently
    0.98
     with
    0.89
     WITH
    0.78
     passionately
    0.77
     strongly
    0.71
     unanimously
    0.70
    lihood
    0.70
    abl
    0.69
     wi
    0.68
     entirely
    0.67
    Act Density 0.049%

    No Known Activations