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

    Neuronpedia

    INDEX
    Explanations

    syntax patterns and operators typically used in programming, particularly loops and incrementations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãģĦãģĭ
    -0.18
    indsight
    -0.15
    /pass
    -0.15
    olan
    -0.14
    ent
    -0.14
    .Cmd
    -0.14
    edin
    -0.14
    paper
    -0.14
    )NULL
    -0.14
    ÑĨенÑĤ
    -0.13
    POSITIVE LOGITS
    lesi
    0.19
    jack
    0.17
    ONA
    0.16
    loat
    0.15
    ordin
    0.15
    rens
    0.14
    loth
    0.14
    728
    0.14
    led
    0.14
    729
    0.14
    Act Density 0.023%

    No Known Activations