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

    Neuronpedia

    INDEX
    Explanations

    strings of numbers

    oai_token-act-pair · gpt-3.5-turbo

    numeric values and alphanumeric sequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    undo
    -0.68
    emort
    -0.68
    asts
    -0.67
    FontSize
    -0.63
    anooga
    -0.61
    ALSE
    -0.61
    âĸ¬
    -0.61
    orest
    -0.58
    agna
    -0.58
     deadlines
    -0.58
    POSITIVE LOGITS
    fb
    0.85
    âĢ³
    0.82
    e
    0.81
    ffe
    0.77
    dc
    0.75
    wm
    0.74
    286
    0.72
    309
    0.72
    ea
    0.72
    a
    0.72
    Act Density 0.043%

    No Known Activations