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

    Neuronpedia

    INDEX
    Explanations

    category labels or classifications within text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    гÑĥ
    -0.16
     Lund
    -0.15
    ollen
    -0.15
     ministry
    -0.14
    жа
    -0.14
    utzer
    -0.14
    LCD
    -0.14
    ordial
    -0.14
    angers
    -0.14
    bow
    -0.14
    POSITIVE LOGITS
    sgi
    0.16
     Priv
    0.15
    readcr
    0.15
    åį
    0.14
    rics
    0.14
    Priv
    0.14
    alsa
    0.14
    voke
    0.14
     Moor
    0.14
     priv
    0.14
    Act Density 0.008%

    No Known Activations