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

    Neuronpedia

    INDEX
    Explanations

    numbers

    oai_token-act-pair · gpt-3.5-turbo

    the frequency of the number 33 in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    »Ĵ
    -0.97
    rolet
    -0.85
    akening
    -0.81
    ĸļ
    -0.79
    oulos
    -0.79
    raints
    -0.77
    mble
    -0.76
    olics
    -0.76
    ItemTracker
    -0.75
    ategory
    -0.74
    POSITIVE LOGITS
    rd
    0.96
    00
    0.94
    333
    0.91
    aan
    0.87
    ¯¯¯¯
    0.82
    RF
    0.79
    DM
    0.76
    LECT
    0.76
    cit
    0.75
    33
    0.73
    Act Density 0.018%

    No Known Activations