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

    Neuronpedia

    INDEX
    Explanations

    actions related to digital activities and processes

    oai_token-act-pair · gpt-3.5-turbo

    actions related to digital content management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orio
    -0.82
    ighth
    -0.66
    juries
    -0.66
    cester
    -0.65
    venth
    -0.61
    idth
    -0.61
    ggies
    -0.60
    joice
    -0.60
    resa
    -0.57
    peria
    -0.57
    POSITIVE LOGITS
     by
    0.90
     beforehand
    0.84
     unanimously
    0.82
     electronically
    0.77
     extensively
    0.77
     somewhere
    0.71
     correctly
    0.71
     offline
    0.71
     retrospect
    0.70
     anonymously
    0.69
    Act Density 0.289%

    No Known Activations