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

    Neuronpedia

    INDEX
    Explanations

    closing brackets followed by numerals or specific punctuation marks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    guess
    -0.16
     Tick
    -0.16
    .gdx
    -0.15
    @Web
    -0.15
    coe
    -0.15
     Ping
    -0.14
    Tick
    -0.14
    auga
    -0.14
    ohana
    -0.14
    @WebServlet
    -0.14
    POSITIVE LOGITS
    ucci
    0.15
    rink
    0.14
     balloons
    0.14
    ãĥĨãĥ«
    0.13
    emi
    0.13
    ê´
    0.13
    CCI
    0.13
    ova
    0.13
    arch
    0.13
    Json
    0.13
    Act Density 0.003%

    No Known Activations