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

    Neuronpedia

    INDEX
    Explanations

    adjectives and nouns related to admiration, fascination, and disgust

    oai_token-act-pair · gpt-3.5-turbo

    emotional responses of admiration, affection, and enthusiasm towards various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     reorgan
    -0.65
    mans
    -0.64
     redund
    -0.64
     helicop
    -0.63
    ModLoader
    -0.61
     antioxid
    -0.60
    ramid
    -0.60
    ewater
    -0.60
    umm
    -0.60
     peanuts
    -0.60
    POSITIVE LOGITS
    acy
    0.88
    ability
    0.87
    fulness
    0.86
    rence
    0.79
    lessness
    0.78
    worthiness
    0.77
     quot
    0.76
     toward
    0.75
    wart
    0.75
    ately
    0.74
    Act Density 0.095%

    No Known Activations