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

    Neuronpedia

    INDEX
    Explanations

    expressions related to improvement or enhancement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arl
    -0.17
     alo
    -0.15
    ostat
    -0.14
     Bend
    -0.14
    ล
    -0.13
    bart
    -0.13
    oir
    -0.13
    Enumerator
    -0.13
    .mi
    -0.13
    uros
    -0.13
    POSITIVE LOGITS
    chas
    0.19
    ora
    0.16
    imate
    0.16
    amaz
    0.14
    imates
    0.14
     Guy
    0.14
     glyphicon
    0.13
    æį·
    0.13
     INTERRUPTION
    0.13
    WithContext
    0.13
    Act Density 0.037%

    No Known Activations