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

    Neuronpedia

    INDEX
    Explanations

    instances of individuals in prominent positions or roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orgh
    -0.15
    ksen
    -0.15
    amespace
    -0.15
    ?option
    -0.14
    otel
    -0.14
     Liberation
    -0.14
    tar
    -0.14
    anz
    -0.14
    istrovstvÃŃ
    -0.14
    Ī¬
    -0.14
    POSITIVE LOGITS
    aghan
    0.15
     CLAIM
    0.15
    flen
    0.15
    áº
    0.14
     fed
    0.14
    èİ
    0.14
    thy
    0.14
     Fleming
    0.14
    anitize
    0.13
    ãĥ§
    0.13
    Act Density 0.345%

    No Known Activations