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

    Neuronpedia

    INDEX
    Explanations

    words related to car engines and performance specifications

    oai_token-act-pair · gpt-3.5-turbo

    abbreviations and acronyms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Pixar
    -0.66
     lest
    -0.64
     fuzzy
    -0.64
    ahime
    -0.64
    bender
    -0.63
    inki
    -0.61
     Takeru
    -0.61
     cour
    -0.61
     Betsy
    -0.60
     knots
    -0.59
    POSITIVE LOGITS
    bilt
    1.17
    opa
    0.80
    emort
    0.77
    ¼
    0.75
    ĪĴ
    0.74
    opal
    0.73
    arious
    0.73
    ¶æ
    0.72
    achev
    0.71
    INAL
    0.69
    Act Density 0.077%

    No Known Activations