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

    Neuronpedia

    INDEX
    Explanations

    verbs related to rejecting or disregarding something

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ood
    -0.66
    olics
    -0.62
    tta
    -0.61
    breeding
    -0.61
    iste
    -0.61
    tti
    -0.60
    ebus
    -0.60
    hedral
    -0.59
     stead
    -0.59
    heric
    -0.58
    POSITIVE LOGITS
    igated
    0.88
     responsibility
    0.87
     outright
    0.85
     aside
    0.85
     accusations
    0.81
    igating
    0.78
     complaints
    0.76
    ively
    0.75
     charges
    0.73
     manslaughter
    0.73
    Act Density 0.069%

    No Known Activations