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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating significant incidents or noteworthy events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eneg
    -0.17
    arme
    -0.16
    reeze
    -0.15
    illion
    -0.15
    heid
    -0.14
    olo
    -0.14
    VEST
    -0.14
    yth
    -0.14
    unte
    -0.14
    earch
    -0.14
    POSITIVE LOGITS
    ernel
    0.17
    ì§
    0.16
    zel
    0.14
     æĬķ稿æĹ¥
    0.14
    deep
    0.14
     Ju
    0.14
    ër
    0.13
     Rolling
    0.13
     ImportError
    0.13
    è½
    0.13
    Act Density 0.424%

    No Known Activations