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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating decision-making processes and preferences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ammen
    -0.17
    kud
    -0.16
    onest
    -0.15
    onen
    -0.15
    usc
    -0.14
    usic
    -0.14
    andles
    -0.14
     sleeper
    -0.14
    abel
    -0.14
    onde
    -0.14
    POSITIVE LOGITS
    ETA
    0.15
    ìŀ¬
    0.15
     Marvin
    0.14
    sid
    0.14
    arger
    0.14
     Phonetic
    0.14
    cta
    0.14
    tae
    0.13
     topo
    0.13
    ARGE
    0.13
    Act Density 0.434%

    No Known Activations