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

    Neuronpedia

    INDEX
    Explanations

    phrases related to truthfulness and errors in judgment

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    Lato
    -0.48
     prochaine
    -0.47
     contrats
    -0.46
     &___
    -0.45
    ğun
    -0.45
     voyez
    -0.45
    ˏ
    -0.45
     choisissez
    -0.43
    __*/
    -0.43
     sinistro
    -0.43
    POSITIVE LOGITS
    rungsseite
    0.70
    *}[
    0.65
    SourceChecksum
    0.63
    ()?;
    0.60
     LoggerFactory
    0.58
    енча
    0.56
    GIVEREF
    0.55
     الرخصة
    0.55
    IsContent
    0.54
    GRANTED
    0.54
    Act Density 0.250%

    No Known Activations