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

    Neuronpedia

    INDEX
    Explanations

    the word "Out" occurring in the text

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific media outlet or program

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     arsen
    -0.78
     compr
    -0.77
    avorite
    -0.73
    iosity
    -0.68
    EStream
    -0.66
     trem
    -0.66
    =-=-=-=-=-=-=-=-
    -0.65
    ãĥŁ
    -0.64
     tyr
    -0.64
     assum
    -0.63
    POSITIVE LOGITS
    doors
    1.14
    stretched
    1.07
    landish
    1.07
    raged
    1.06
    rage
    1.04
    fitted
    1.03
    lander
    1.02
    skirts
    0.99
    wards
    0.98
    numbered
    0.98
    Act Density 0.030%

    No Known Activations