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

    Neuronpedia

    INDEX
    Explanations

    references to thoughts or commentary in discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    beit
    -0.15
    gings
    -0.14
    preload
    -0.14
    her
    -0.14
    ème
    -0.14
    ingle
    -0.14
    ingham
    -0.14
    коÑĢ
    -0.14
    øre
    -0.14
    erset
    -0.14
    POSITIVE LOGITS
     novice
    0.15
    ľ
    0.14
    Ñı
    0.14
    APT
    0.14
    ombat
    0.14
     оно
    0.14
    ARAM
    0.13
    APTER
    0.13
    ruk
    0.13
     trip
    0.13
    Act Density 0.002%

    No Known Activations