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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Rick
    -0.15
    ValuePair
    -0.15
    fout
    -0.14
    곡
    -0.14
     susp
    -0.14
     exp
    -0.14
    eln
    -0.14
    ConverterFactory
    -0.14
     qw
    -0.14
    endet
    -0.14
    POSITIVE LOGITS
    addock
    0.15
    .rmi
    0.15
    owitz
    0.15
    quel
    0.14
    uth
    0.14
    ceed
    0.14
    cul
    0.13
    idd
    0.13
    ced
    0.13
    ovit
    0.13
    Act Density 0.002%

    No Known Activations