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

    Neuronpedia

    INDEX
    Explanations

    specific geographic locations and technical component initialization phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     eskort
    -0.18
    çĢ
    -0.16
    mask
    -0.15
    gend
    -0.15
    .Guna
    -0.15
    uant
    -0.14
    inq
    -0.14
    ụ
    -0.14
    QualifiedName
    -0.14
    pery
    -0.14
    POSITIVE LOGITS
    ritte
    0.16
    골
    0.16
     Loft
    0.15
    Ł
    0.15
    ivant
    0.15
    ¤ëĭ¤
    0.14
     bunk
    0.14
    arness
    0.14
    anded
    0.14
     shapes
    0.14
    Act Density 0.000%

    No Known Activations