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

    Neuronpedia

    INDEX
    Explanations

    phrases related to confirmation, registration, or verification

    oai_token-act-pair · gpt-3.5-turbo

    the existence and state of entities or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Hyder
    -0.68
     stalls
    -0.63
     senses
    -0.61
     Franch
    -0.59
     haul
    -0.58
     Naj
    -0.58
     Hawks
    -0.58
     races
    -0.57
     Marse
    -0.57
     congr
    -0.57
    POSITIVE LOGITS
     nevertheless
    0.79
    Ĥİ
    0.77
    ById
    0.75
    rael
    0.75
     nonetheless
    0.73
    daq
    0.72
    senal
    0.72
    KER
    0.70
    wolves
    0.70
     actually
    0.68
    Act Density 0.342%

    No Known Activations