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

    Neuronpedia

    INDEX
    Explanations

    references to online engagement and content visibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÎķÎĻ
    -0.17
     Wr
    -0.16
    çŃĴ
    -0.16
    mour
    -0.15
     Merr
    -0.14
    inan
    -0.14
    stup
    -0.14
    rack
    -0.14
    ocaly
    -0.14
     Ves
    -0.14
    POSITIVE LOGITS
    igel
    0.15
     Rhodes
    0.15
    rollo
    0.14
    implify
    0.14
    ousel
    0.14
    weg
    0.14
    dings
    0.14
    uess
    0.14
    uzzer
    0.14
    ade
    0.14
    Act Density 0.002%

    No Known Activations