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

    Neuronpedia

    INDEX
    Explanations

    negative sentiments expressed through verbs

    oai_token-act-pair · gpt-3.5-turbo

    negations and the expressions of desire or denial

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     mutual
    -0.66
     indexes
    -0.61
    Versions
    -0.60
     depos
    -0.60
    gap
    -0.59
     intra
    -0.59
     selves
    -0.58
    Higher
    -0.57
    Recommend
    -0.57
     exchange
    -0.56
    POSITIVE LOGITS
    acus
    0.81
    zsche
    0.75
     wonders
    0.74
     renown
    0.73
     himself
    0.72
    itone
    0.71
    ĸļ
    0.71
     fame
    0.70
     brilliantly
    0.69
     herself
    0.67
    Act Density 0.477%

    No Known Activations