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

    Neuronpedia

    INDEX
    Explanations

    words related to abilities and actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     eps
    -0.15
    yntax
    -0.15
    PEnd
    -0.14
    rowned
    -0.14
     èIJ
    -0.14
     TIMEOUT
    -0.14
     boutique
    -0.14
    ालà¤ķ
    -0.13
    erule
    -0.13
    olt
    -0.13
    POSITIVE LOGITS
    ten
    0.17
    emek
    0.16
    سÙĥ
    0.16
    ardy
    0.15
    yte
    0.15
     sche
    0.15
    rys
    0.15
    aru
    0.15
    rzy
    0.15
    olin
    0.15
    Act Density 0.184%

    No Known Activations