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

    Neuronpedia

    INDEX
    Explanations

    mentions of the outcome of a game or match

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ican
    -0.68
    onte
    -0.65
    ailability
    -0.61
     gearing
    -0.59
    essage
    -0.57
    £ı
    -0.56
     therap
    -0.55
    velength
    -0.54
     tremend
    -0.54
     unden
    -0.54
    POSITIVE LOGITS
    cards
    0.83
    friend
    0.82
    card
    0.74
    strings
    0.66
    backs
    0.66
    STON
    0.64
    ered
    0.63
    lings
    0.62
    hack
    0.62
    erers
    0.61
    Act Density 6.818%

    No Known Activations