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

    Neuronpedia

    INDEX
    Explanations

    terms related to transition and transformation concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ices
    -0.17
    oop
    -0.16
    ong
    -0.15
    adius
    -0.15
    ows
    -0.14
    ÑĤаÑĢ
    -0.14
    strap
    -0.14
    ouch
    -0.14
    atsby
    -0.14
    ÑĢай
    -0.14
    POSITIVE LOGITS
    /trans
    0.29
    aksi
    0.27
    ylvania
    0.22
    -trans
    0.20
    ylv
    0.20
    .trans
    0.18
    verse
    0.18
    sexual
    0.18
    mere
    0.17
    (trans
    0.17
    Act Density 0.041%

    No Known Activations