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

    Neuronpedia

    INDEX
    Explanations

    facts or statements presented as supporting evidence for an argument or claim

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     nomine
    -0.60
     <=",
    -0.59
     solidar
    -0.59
     aspira
    -0.54
     Geografia
    -0.53
    IntoConstraints
    -0.53
     veter
    -0.53
    SourceChecksum
    -0.53
     Hva
    -0.52
     noten
    -0.52
    POSITIVE LOGITS
     disreg
    0.97
     unspeak
    0.91
     apprehen
    0.87
     cushi
    0.85
     hairc
    0.81
     gaily
    0.81
     cuck
    0.80
     unwarran
    0.80
     ineffec
    0.79
     pooh
    0.77
    Act Density 0.079%

    No Known Activations