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

    Neuronpedia

    INDEX
    Explanations

    mentions of media outlets

    oai_token-act-pair · gpt-3.5-turbo

    references to media outlets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    heed
    -0.70
    eric
    -0.70
    sil
    -0.63
    jri
    -0.61
    itational
    -0.58
     Lama
    -0.57
    imm
    -0.57
    union
    -0.57
    olds
    -0.57
    ipeg
    -0.56
    POSITIVE LOGITS
     outlet
    1.12
     outlets
    1.10
    swick
    0.86
     ende
    0.73
    ="#
    0.68
    stadt
    0.68
    lisher
    0.67
    £ı
    0.67
    icago
    0.66
    eval
    0.66
    Act Density 0.022%

    No Known Activations