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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "just" followed by a number indicating time or quantity

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "just"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xual
    -0.76
     cous
    -0.73
    idon
    -0.73
     confir
    -0.70
     challeng
    -0.69
    ixel
    -0.66
    glomer
    -0.65
    anwhile
    -0.62
     PLUS
    -0.62
    pora
    -0.61
    POSITIVE LOGITS
    ifiable
    1.18
    ifications
    1.13
    ices
    0.93
    IFIC
    0.92
    ICES
    0.91
    IFIED
    0.91
    itia
    0.89
    ifi
    0.86
    if
    0.83
    ifiers
    0.78
    Act Density 0.103%

    No Known Activations