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

    Neuronpedia

    INDEX
    Explanations

    programming terminology and structures related to code or metadata

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .omg
    -0.16
    oir
    -0.15
    veis
    -0.15
     promin
    -0.15
    TW
    -0.14
    ubar
    -0.14
    ÑĥÑĪка
    -0.14
    meer
    -0.14
    rise
    -0.14
    lags
    -0.13
    POSITIVE LOGITS
    OPY
    0.14
    lius
    0.14
    /***/
    0.14
    rane
    0.14
     Soldier
    0.14
     pit
    0.14
    Cast
    0.13
    ı
    0.13
     tolerance
    0.13
    deaux
    0.13
    Act Density 0.001%

    No Known Activations