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

    Neuronpedia

    INDEX
    Explanations

    words related to contrasting actions or concepts

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a distinction between individual actions and societal influences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     WATCHED
    -0.77
    mun
    -0.69
    ļéĨĴ
    -0.68
    uel
    -0.60
    Status
    -0.59
    Ļ½
    -0.59
     Flavoring
    -0.58
    tenance
    -0.57
     Strongh
    -0.57
     periodically
    -0.56
    POSITIVE LOGITS
     necessarily
    0.83
     ones
    0.80
     nor
    0.80
     slightest
    0.76
     mention
    0.70
     anything
    0.68
     anymore
    0.66
     anywhere
    0.65
    YP
    0.65
    zes
    0.63
    Act Density 0.161%

    No Known Activations