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

    Neuronpedia

    INDEX
    Explanations

    key actors and their performances in film and television reviews

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hiba
    -0.15
    relude
    -0.15
    srv
    -0.15
    alloween
    -0.15
    aby
    -0.15
    _intr
    -0.14
    oration
    -0.14
    ubbo
    -0.14
    blade
    -0.14
    бÑĥ
    -0.14
    POSITIVE LOGITS
    饰
    0.17
    ÙĪØŃ
    0.16
    IFY
    0.14
    .uml
    0.14
    飾
    0.14
    hoff
    0.14
    tsky
    0.13
    -HT
    0.13
    ?↵↵↵↵
    0.13
    bjerg
    0.13
    Act Density 0.091%

    No Known Activations