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

    Neuronpedia

    INDEX
    Explanations

    words related to intention or goals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    agan
    -0.18
    .Compiler
    -0.17
    agas
    -0.15
    _submenu
    -0.15
     elect
    -0.14
    .addProperty
    -0.14
    uku
    -0.14
    oku
    -0.14
    rame
    -0.14
    .UIManager
    -0.14
    POSITIVE LOGITS
     Ign
    0.16
     ign
    0.16
    gross
    0.15
     Neg
    0.15
     chains
    0.15
     Chains
    0.14
    Ign
    0.14
    atha
    0.14
    ign
    0.14
    969
    0.14
    Act Density 0.000%

    No Known Activations