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

    Neuronpedia

    INDEX
    Explanations

    keywords related to text input and user interface interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abeth
    -0.17
    èµ·
    -0.14
    oints
    -0.14
     Lie
    -0.14
    alf
    -0.14
    ault
    -0.14
    åİļ
    -0.14
    ãĥĬãĥ¼
    -0.14
     patched
    -0.14
     hypoc
    -0.13
    POSITIVE LOGITS
    abay
    0.17
    adan
    0.16
    LEAR
    0.16
    esel
    0.15
    phins
    0.15
    ávÄĽ
    0.15
    ipheral
    0.14
    arent
    0.14
    rending
    0.14
    è²¼
    0.14
    Act Density 0.245%

    No Known Activations