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

    Neuronpedia

    INDEX
    Explanations

    references to free offers and promotions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Ñģвобод
    -0.19
     вÑĸлÑĮ
    -0.17
    _free
    -0.16
     free
    -0.16
    frei
    -0.15
    llum
    -0.15
    FREE
    -0.15
     FREE
    -0.15
    èĩªçĶ±
    -0.15
    _FREE
    -0.15
    POSITIVE LOGITS
    bies
    0.52
    bie
    0.50
    zers
    0.36
    zing
    0.35
    zer
    0.33
    -standing
    0.32
    ze
    0.31
    -of
    0.31
    zes
    0.30
    bee
    0.30
    Act Density 0.052%

    No Known Activations