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

    Neuronpedia

    INDEX
    Explanations

    references to hair types and characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    illac
    -0.18
    emouth
    -0.18
    usto
    -0.17
    ut
    -0.16
    raya
    -0.15
    askell
    -0.14
    lech
    -0.14
    lex
    -0.14
    eteria
    -0.14
    ansen
    -0.14
    POSITIVE LOGITS
    conditionally
    0.15
    bÃŃ
    0.14
    .Invariant
    0.14
     blanks
    0.14
    asters
    0.14
    )throws
    0.14
    ITE
    0.14
    нок
    0.14
    .vertx
    0.14
    еÑģÑĤи
    0.14
    Act Density 0.045%

    No Known Activations