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

    Neuronpedia

    INDEX
    Explanations

    statements related to online content monitoring and submission guidelines

    oai_token-act-pair · gpt-3.5-turbo

    phrases or terms related to content management and user interaction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Rib
    -0.63
     tongues
    -0.59
     epit
    -0.58
    verages
    -0.57
    geist
    -0.54
     prem
    -0.54
     Symb
    -0.54
     mart
    -0.53
    ged
    -0.52
    gow
    -0.51
    POSITIVE LOGITS
    Ĥİ
    0.68
     {*
    0.68
    anyl
    0.64
    çİĭ
    0.63
    £ı
    0.63
    osion
    0.62
    fml
    0.61
    pload
    0.61
    reality
    0.60
    leon
    0.60
    Act Density 0.102%

    No Known Activations