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

    Neuronpedia

    INDEX
    Explanations

    teams and group-related terms

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     Investor
    -0.68
    grain
    -0.68
     deterrent
    -0.65
    alam
    -0.64
    trade
    -0.63
     prohibitions
    -0.62
     taboo
    -0.61
     taxpayer
    -0.60
     statute
    -0.60
    cible
    -0.60
    POSITIVE LOGITS
     disbanded
    1.61
     comprised
    1.56
     consisted
    1.49
     consisting
    1.46
     assembled
    1.40
    members
    1.31
     composed
    1.28
     comprising
    1.24
     consists
    1.23
     formed
    1.19
    Act Density 0.376%

    No Known Activations