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

    Neuronpedia

    INDEX
    Explanations

    questions and expressions of confusion or disbelief

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ALSE
    -0.15
    loff
    -0.14
    hs
    -0.14
    undler
    -0.14
    ELS
    -0.14
    änd
    -0.14
    .strict
    -0.14
    zyst
    -0.14
    mise
    -0.14
    aç
    -0.13
    POSITIVE LOGITS
    icate
    0.15
    dump
    0.14
    gtest
    0.14
     exactly
    0.14
    XHR
    0.14
    tol
    0.14
    ê
    0.14
    rones
    0.13
    allocator
    0.13
    ÑĩеÑĤ
    0.13
    Act Density 0.148%

    No Known Activations