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

    Neuronpedia

    INDEX
    Explanations

    specific numeric values and references in a technical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    andbox
    -0.15
    okus
    -0.14
    roud
    -0.14
    emento
    -0.14
    punk
    -0.13
    elf
    -0.13
    miÅŁ
    -0.13
     Sherman
    -0.13
     cord
    -0.13
    atorium
    -0.13
    POSITIVE LOGITS
    forman
    0.15
    asan
    0.15
    lesen
    0.14
    erken
    0.14
    igel
    0.14
    аки
    0.13
    .gf
    0.13
    egal
    0.13
    ÃĹ</
    0.13
    alker
    0.13
    Act Density 0.031%

    No Known Activations