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

    Neuronpedia

    INDEX
    Explanations

    significant contextual markers and pivotal verbs that indicate change or action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orsi
    -0.15
    173
    -0.15
     Ballard
    -0.15
     majority
    -0.15
    abel
    -0.15
    erti
    -0.14
    onda
    -0.14
    168
    -0.14
     consistent
    -0.14
    ILING
    -0.13
    POSITIVE LOGITS
    ajas
    0.17
    erville
    0.16
    ajs
    0.15
    eways
    0.15
    ]byte
    0.15
    ocale
    0.14
    anlı
    0.14
    atik
    0.14
    abwe
    0.14
    mÄĽ
    0.14
    Act Density 0.009%

    No Known Activations