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

    Neuronpedia

    INDEX
    Explanations

    occurrences of words related to acceptance and approval

    oai_token-act-pair · gpt-3.5-turbo

    references to acceptance, particularly regarding offers, payments, and social responsibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     wre
    -0.64
    gallery
    -0.64
    mAh
    -0.63
    ginx
    -0.60
     Tycoon
    -0.60
    inka
    -0.60
     pockets
    -0.60
    acco
    -0.60
    abouts
    -0.59
     Alley
    -0.59
    POSITIVE LOGITS
     invitation
    0.87
     uncond
    0.86
     unres
    0.82
     gladly
    0.79
    aram
    0.77
     willingly
    0.74
     voluntarily
    0.71
     forgiveness
    0.70
     premise
    0.68
     responsibility
    0.67
    Act Density 0.184%

    No Known Activations