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

    Neuronpedia

    INDEX
    Explanations

    expressions of surprise or exclamation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eon
    -0.16
    yk
    -0.15
    $MESS
    -0.15
    ubic
    -0.15
    dol
    -0.15
    foon
    -0.14
    ÑĤаб
    -0.14
    azÄĥ
    -0.14
    oard
    -0.14
     wink
    -0.14
    POSITIVE LOGITS
    _CPP
    0.17
     nackte
    0.15
    roups
    0.15
    980
    0.14
    γει
    0.14
    ysics
    0.14
    esen
    0.14
    odies
    0.13
     gratuites
    0.13
     TypeInfo
    0.13
    Act Density 0.031%

    No Known Activations