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

    Neuronpedia

    INDEX
    Explanations

    terms related to actions or processes involving various topics

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing the importance or impact of various subjects or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Refresh
    -0.72
     Tsukuyomi
    -0.69
    imum
    -0.64
     sap
    -0.63
    imal
    -0.63
     Leaves
    -0.62
    onement
    -0.61
     Cups
    -0.61
     shy
    -0.60
     +/-
    -0.59
    POSITIVE LOGITS
     ALSO
    0.82
     actively
    0.81
     also
    0.79
    also
    0.79
    literally
    0.72
    paces
    0.67
    feature
    0.66
    !]
    0.63
    eta
    0.63
    Secondly
    0.63
    Act Density 0.283%

    No Known Activations