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

    Neuronpedia

    INDEX
    Explanations

    statements related to verification or checking of information or facts

    oai_token-act-pair · gpt-3.5-turbo

    mentions of factual claims or assertions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     offence
    -0.69
    creen
    -0.66
     clerk
    -0.65
    haw
    -0.64
    taboola
    -0.64
     nm
    -0.63
     deed
    -0.62
     ransom
    -0.61
    lihood
    -0.61
    DER
    -0.58
    POSITIVE LOGITS
    eworks
    0.83
    ilitation
    0.74
    tis
    0.74
    enza
    0.72
    ptive
    0.72
    Myth
    0.71
    eless
    0.71
    DonaldTrump
    0.71
     Tire
    0.70
    iled
    0.70
    Act Density 0.029%

    No Known Activations