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

    Neuronpedia

    INDEX
    Explanations

    words related to hypothetical situations or speculative discussions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    sbm
    -0.79
    arks
    -0.72
     Companies
    -0.71
    aspers
    -0.69
     Tackle
    -0.68
    endas
    -0.64
    aughs
    -0.64
     Leone
    -0.63
    Phones
    -0.63
    inis
    -0.62
    POSITIVE LOGITS
     explanation
    0.73
    place
    0.72
     indication
    0.71
     savior
    0.70
     miraculous
    0.69
     grounding
    0.69
     semblance
    0.69
     intermediary
    0.69
    ciplinary
    0.67
     mythical
    0.67
    Act Density 0.023%

    No Known Activations