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

    Neuronpedia

    INDEX
    Explanations

    phrases that present alternative perspectives or restate previous ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    jectory
    -0.16
    .gdx
    -0.15
    غ
    -0.15
    ylon
    -0.15
    Ñĩен
    -0.15
    .Flag
    -0.14
    brero
    -0.14
    eyn
    -0.14
    exion
    -0.14
    pk
    -0.14
    POSITIVE LOGITS
     *__
    0.15
    aggi
    0.15
     basically
    0.14
    Raster
    0.14
    eti
    0.14
    agina
    0.14
    068
    0.14
    orer
    0.13
    otas
    0.13
    779
    0.13
    Act Density 0.032%

    No Known Activations