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

    Neuronpedia

    INDEX
    Explanations

    phrases related to guidance and decision-making processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ADOR
    -0.15
    .appspot
    -0.15
    à¸ķร
    -0.15
    atoria
    -0.14
    ador
    -0.14
    adores
    -0.14
    úsqueda
    -0.14
    amespace
    -0.14
    istan
    -0.13
    Od
    -0.13
    POSITIVE LOGITS
    наÑĩе
    0.18
    æĬľ
    0.15
     otherwise
    0.15
    DOT
    0.14
    gom
    0.14
     allied
    0.14
     therein
    0.13
     Gol
    0.13
     Trucks
    0.13
    utan
    0.13
    Act Density 0.820%

    No Known Activations