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

    Neuronpedia

    INDEX
    Explanations

    fictional creatures or names associated with a playful context

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    stocks
    -0.64
     Dominion
    -0.63
    redits
    -0.61
     Bots
    -0.59
     Harbour
    -0.59
     tenancy
    -0.59
    still
    -0.59
    intosh
    -0.56
     Zimbabwe
    -0.56
     Scotia
    -0.55
    POSITIVE LOGITS
    terday
    0.96
    ory
    0.95
    ational
    0.89
    atory
    0.87
    cript
    0.85
    hed
    0.85
    edIn
    0.84
    ibles
    0.83
    iq
    0.81
    orical
    0.81
    Act Density 0.055%

    No Known Activations