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

    Neuronpedia

    INDEX
    Explanations

    relationships between characters and their roles or identities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÑĢÑĥÑĤ
    -0.14
    strtotime
    -0.13
    коп
    -0.13
     Backbone
    -0.13
    اÙĪر
    -0.13
    ingleton
    -0.13
    à¸ļาล
    -0.13
    atron
    -0.13
    ppo
    -0.13
    ket
    -0.13
    POSITIVE LOGITS
     called
    0.46
    called
    0.41
    åı«
    0.37
     Called
    0.36
     named
    0.35
    Called
    0.34
    -called
    0.32
     llam
    0.31
    named
    0.29
     titled
    0.28
    Act Density 0.257%

    No Known Activations