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

    Neuronpedia

    INDEX
    Explanations

    original content or information

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "original" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wal
    -0.78
    robe
    -0.74
    walk
    -0.72
    =-=-=-=-=-=-=-=-
    -0.71
    ega
    -0.70
    rom
    -0.68
     Simulator
    -0.67
    inging
    -0.65
    angs
    -0.65
    opping
    -0.64
    POSITIVE LOGITS
    ity
    1.05
    ITY
    1.00
     incarnation
    0.85
    itized
    0.75
     impetus
    0.74
     trilogy
    0.74
     batch
    0.73
    lly
    0.72
     poster
    0.72
    Filename
    0.71
    Act Density 0.022%

    No Known Activations