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

    Neuronpedia

    INDEX
    Explanations

    interactions involving persuasion and familial relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erule
    -0.16
    fsp
    -0.15
    inox
    -0.15
    arel
    -0.15
    ritel
    -0.14
     Pant
    -0.14
    wcs
    -0.14
    ustos
    -0.14
    -valu
    -0.13
    è³Ģ
    -0.13
    POSITIVE LOGITS
     convince
    0.43
    pers
    0.42
    conv
    0.41
     persuade
    0.40
     convincing
    0.38
     convin
    0.38
     Conv
    0.38
     persu
    0.36
     Pers
    0.36
     thuyết
    0.35
    Act Density 0.473%

    No Known Activations