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

    Neuronpedia

    INDEX
    Explanations

    instances of general information and instructions about various topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    :UIAlert
    -0.16
    kle
    -0.16
     Kahn
    -0.15
    itesse
    -0.15
    retty
    -0.14
    énom
    -0.14
    kah
    -0.14
    ARAM
    -0.14
    ulan
    -0.14
    ATRIX
    -0.13
    POSITIVE LOGITS
     provision
    0.14
    olf
    0.13
    Ñľ
    0.13
    ergy
    0.13
    utin
    0.12
    Æ¡i
    0.12
    _iters
    0.12
     upt
    0.12
    ewire
    0.12
    äll
    0.12
    Act Density 0.497%

    No Known Activations