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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific names or terms preceded by the letters "th"

    oai_token-act-pair · gpt-3.5-turbo

    tokens and references related to programming and web development

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     IB
    -0.71
    adi
    -0.71
    Ãį
    -0.70
    IB
    -0.68
     Bray
    -0.63
    ÃŃ
    -0.62
     Dominic
    -0.62
     Beh
    -0.62
    IC
    -0.62
     Kah
    -0.62
    POSITIVE LOGITS
    on
    1.04
    onson
    0.96
    pan
    0.86
    On
    0.85
    onian
    0.85
    ons
    0.84
     on
    0.82
    upon
    0.82
    untu
    0.78
    ón
    0.78
    Act Density 0.162%

    No Known Activations