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

    Neuronpedia

    INDEX
    Explanations

    references to the individual named "Tor" and associations with him

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     reluct
    -0.82
     maneu
    -0.76
     gaily
    -0.73
     tolerably
    -0.72
     plenti
    -0.72
     disagre
    -0.70
     nobly
    -0.70
     unspeak
    -0.70
     shenan
    -0.69
    /**
    -0.69
    POSITIVE LOGITS
     Tor
    1.47
    Tor
    1.39
     tor
    1.27
     TOR
    1.22
    tor
    1.12
    TOR
    1.10
     Torrance
    0.77
     Torrey
    0.76
     torsion
    0.75
     TORT
    0.73
    Act Density 0.099%

    No Known Activations