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

    Neuronpedia

    INDEX
    Explanations

    references to small quantities or degrees

    oai_token-act-pair · gpt-3.5-turbo

    variations of the phrase "a little" indicating small amounts or degrees

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    osponsors
    -0.91
    eneg
    -0.81
    ourses
    -0.78
    orthy
    -0.77
    emale
    -0.74
    idents
    -0.73
    ayn
    -0.72
    views
    -0.72
    yss
    -0.72
    ufact
    -0.71
    POSITIVE LOGITS
     bit
    1.55
     BIT
    0.91
     girl
    0.82
     extra
    0.79
     Bit
    0.79
     peek
    0.78
     tad
    0.77
     somet
    0.76
     kid
    0.75
    bit
    0.75
    Act Density 0.041%

    No Known Activations