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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing quantifiers and examples

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    758
    -0.16
    wei
    -0.15
    etur
    -0.14
    enc
    -0.14
    ulist
    -0.14
    еди
    -0.14
     itself
    -0.13
     into
    -0.13
    ç£
    -0.13
    ases
    -0.13
    POSITIVE LOGITS
    esson
    0.17
    aises
    0.16
    apons
    0.15
    iyim
    0.15
    icker
    0.15
     Masc
    0.14
    iked
    0.14
    iola
    0.14
    hower
    0.14
    mmas
    0.14
    Act Density 0.030%

    No Known Activations