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

    Neuronpedia

    INDEX
    Explanations

    technical terms or phrases

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to programming and technical processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vernment
    -0.69
     Rodham
    -0.63
    intend
    -0.63
    partisan
    -0.61
     Sinclair
    -0.57
     Journalists
    -0.56
    rollers
    -0.56
    ergy
    -0.55
    justice
    -0.55
    bernatorial
    -0.55
    POSITIVE LOGITS
    catentry
    0.75
    )).
    0.74
     exceptions
    0.73
     attRot
    0.73
     corresponding
    0.68
     recommends
    0.66
     accordingly
    0.65
    pecially
    0.65
    ?).
    0.64
    SourceFile
    0.64
    Act Density 1.493%

    No Known Activations