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

    Neuronpedia

    INDEX
    Explanations

    terms related to liability and damages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xo
    -0.17
    ghi
    -0.17
     Rich
    -0.15
    Typed
    -0.14
    ikel
    -0.14
    906
    -0.14
    ÃŃk
    -0.14
     diseñador
    -0.14
    net
    -0.13
     Pap
    -0.13
    POSITIVE LOGITS
    ukes
    0.15
    ullet
    0.15
    adies
    0.15
    vang
    0.14
    vap
    0.14
    _Reset
    0.13
    ãĥĥãĤ°
    0.13
     Grat
    0.13
    _BITMAP
    0.13
    ìĨIJ
    0.13
    Act Density 0.031%

    No Known Activations