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

    Neuronpedia

    INDEX
    Explanations

    references to academic papers and citations within research contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fell
    -0.18
    aring
    -0.17
    ophile
    -0.15
    auce
    -0.15
    çķ
    -0.14
    ÑĦиÑĨи
    -0.14
    íĬ
    -0.14
    ARS
    -0.14
    mund
    -0.14
    ipel
    -0.14
    POSITIVE LOGITS
    dain
    0.16
    htable
    0.15
     tack
    0.14
    .sat
    0.14
    pio
    0.14
    idar
    0.14
    HITE
    0.14
     crafts
    0.13
    Interpreter
    0.13
    çį¨
    0.13
    Act Density 0.165%

    No Known Activations