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

    Neuronpedia

    INDEX
    Explanations

    comparative phrases that imply a distinction or preference between two entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .za
    -0.16
    pear
    -0.16
     Hercules
    -0.14
    оÑĢож
    -0.14
    ERÄ°
    -0.13
    JsonValue
    -0.13
    Äįin
    -0.13
    _SCOPE
    -0.13
     uncert
    -0.13
    ÑĨей
    -0.12
    POSITIVE LOGITS
    others
    0.19
     others
    0.16
     ones
    0.16
    ãĥ©ãĥ¼
    0.15
    monds
    0.14
    oldt
    0.14
    ledo
    0.14
    kla
    0.14
    isia
    0.14
     fare
    0.14
    Act Density 0.084%

    No Known Activations