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

    Neuronpedia

    INDEX
    Explanations

    terms related to legal matters and evidence collection

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to legal and ethical violations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     HIT
    -0.78
    Rap
    -0.77
    SHIP
    -0.66
     GN
    -0.64
    eatures
    -0.64
    obal
    -0.64
    Aut
    -0.63
    nen
    -0.63
     Mock
    -0.63
    iosyn
    -0.60
    POSITIVE LOGITS
     syndrome
    0.75
    !,
    0.69
    "}],"
    0.66
     (%)
    0.66
     etc
    0.65
     ¯
    0.65
     ¶
    0.64
     (?,
    0.63
     Baird
    0.61
     (
    0.60
    Act Density 0.685%

    No Known Activations