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

    Neuronpedia

    INDEX
    Explanations

    adverbs and adjectives indicating fairness or correctness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    éric
    -0.16
    qli
    -0.15
    Æ°ng
    -0.15
    ERRU
    -0.14
    illery
    -0.14
    erman
    -0.14
    WEEN
    -0.14
    mint
    -0.14
    undi
    -0.14
     Gran
    -0.14
    POSITIVE LOGITS
    zı
    0.16
    uja
    0.15
    ipe
    0.14
    fully
    0.14
    atatype
    0.14
    ór
    0.14
    åĬ
    0.14
     advant
    0.13
    _FIELDS
    0.13
    igth
    0.13
    Act Density 0.011%

    No Known Activations