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

    Neuronpedia

    INDEX
    Explanations

    words related to intentions and making decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ilan
    -0.15
    ç¿°
    -0.14
    rys
    -0.14
    Reuse
    -0.14
    Decorator
    -0.14
    rollers
    -0.14
     cầm
    -0.14
     Smarty
    -0.14
     unre
    -0.14
    angen
    -0.14
    POSITIVE LOGITS
    κή
    0.15
    itzer
    0.14
    .listeners
    0.14
    uy
    0.14
    oug
    0.14
    ankan
    0.13
    ÑĤеÑĢи
    0.13
     Bod
    0.13
    ager
    0.13
    ernet
    0.13
    Act Density 0.000%

    No Known Activations