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

    Neuronpedia

    INDEX
    Explanations

    mentions of indoor locations or activities

    oai_token-act-pair · gpt-3.5-turbo

    references to indoor activities and mentions related to ankles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lda
    -0.68
    urai
    -0.67
    ebin
    -0.67
    sburg
    -0.67
     Called
    -0.66
    making
    -0.66
    arations
    -0.64
     Canaver
    -0.64
    awed
    -0.64
    rior
    -0.63
    POSITIVE LOGITS
    iencies
    0.79
     indoor
    0.75
     plumbing
    0.73
     dome
    0.72
    ysis
    0.69
    estinal
    0.66
     attic
    0.66
    spect
    0.65
    atus
    0.64
     Monitor
    0.61
    Act Density 0.049%

    No Known Activations