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

    Neuronpedia

    INDEX
    Explanations

    verbs related to persuasion or influence

    oai_token-act-pair · gpt-3.5-turbo

    words associated with manipulation and persuasion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     effected
    -0.73
    externalActionCode
    -0.71
     Skydragon
    -0.68
     surg
    -0.65
    icut
    -0.62
     footprint
    -0.60
    hattan
    -0.60
     closely
    -0.59
    anwhile
    -0.58
     photograp
    -0.58
    POSITIVE LOGITS
     excuses
    0.80
     suggestions
    0.79
     assurances
    0.76
     virtues
    0.74
    ATURES
    0.72
     opinions
    0.72
     praise
    0.70
    eers
    0.69
     endorsements
    0.69
     Parables
    0.68
    Act Density 0.190%

    No Known Activations