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

    Neuronpedia

    INDEX
    Explanations

    verbs related to persuading or enticing someone

    oai_token-act-pair · gpt-3.5-turbo

    verbs associated with persuasion and attraction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arna
    -0.69
     reckoning
    -0.66
    andro
    -0.61
    Ü
    -0.60
     injust
    -0.60
     Blaz
    -0.60
     Penalty
    -0.59
    arium
    -0.59
    alach
    -0.59
    inances
    -0.59
    POSITIVE LOGITS
     lure
    0.89
     unsuspecting
    0.88
    glers
    0.88
     gull
    0.87
     lured
    0.85
     unwitting
    0.82
    pter
    0.82
    NetMessage
    0.74
     woo
    0.71
     blackmail
    0.69
    Act Density 0.096%

    No Known Activations