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

    Neuronpedia

    INDEX
    Explanations

    words related to persuasion or influence

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "convince" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nam
    -0.77
    OIL
    -0.72
    illary
    -0.69
    abytes
    -0.68
    owment
    -0.68
    lain
    -0.67
    practice
    -0.66
    eworthy
    -0.65
    alm
    -0.64
    endor
    -0.64
    POSITIVE LOGITS
    ingly
    0.91
    tale
    0.88
    ments
    0.81
     convinc
    0.80
     skeptics
    0.76
     convince
    0.73
     reluctant
    0.72
     convinced
    0.72
    ment
    0.70
     voters
    0.69
    Act Density 0.030%

    No Known Activations