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

    Neuronpedia

    INDEX
    Explanations

    dates and numerical information

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to regulatory and safety actions in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    facing
    -0.70
    nikov
    -0.70
     Joker
    -0.59
    aples
    -0.57
     Ghostbusters
    -0.56
    lda
    -0.56
    essing
    -0.56
    opped
    -0.55
     Sands
    -0.55
     mound
    -0.55
    POSITIVE LOGITS
    ICA
    0.80
    ITION
    0.75
    exempt
    0.73
    senal
    0.71
     acronym
    0.70
    LET
    0.70
    lishes
    0.69
    soDeliveryDate
    0.68
     disbanded
    0.68
    ENE
    0.67
    Act Density 0.566%

    No Known Activations