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

    Neuronpedia

    INDEX
    Explanations

    variants of words and prefixes/suffixes commonly used in English

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zcze
    -0.16
    zÄĻ
    -0.15
    chwitz
    -0.15
    umas
    -0.15
    xda
    -0.14
    747
    -0.14
    taboola
    -0.14
    ãĥ¼ãĥĨ
    -0.14
    ziel
    -0.14
    zig
    -0.14
    POSITIVE LOGITS
    atre
    0.19
    /latest
    0.14
    ook
    0.14
    odore
    0.14
    /etc
    0.14
    on
    0.14
    eton
    0.14
    allery
    0.13
    .decorate
    0.13
    h
    0.13
    Act Density 0.077%

    No Known Activations