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

    Neuronpedia

    INDEX
    Explanations

    numbers written in words

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Fif" and variations related to quantities, particularly the number six

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    icably
    -0.81
     Obst
    -0.73
    ensical
    -0.70
    ocl
    -0.69
    iger
    -0.69
     conscience
    -0.68
    iller
    -0.67
    icable
    -0.65
    itton
    -0.64
    sync
    -0.64
    POSITIVE LOGITS
    teen
    1.62
    teenth
    1.19
    heed
    0.93
    ths
    0.89
    th
    0.86
    ty
    0.82
    sie
    0.80
    Sax
    0.79
    mented
    0.79
    ters
    0.78
    Act Density 0.042%

    No Known Activations