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

    Neuronpedia

    INDEX
    Explanations

    terminology related to specific numbers or counts in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    flt
    -0.16
     Ãĸz
    -0.15
    ارج
    -0.15
    ãĥªãĥ¼
    -0.14
    .arch
    -0.14
     ÙħتØŃ
    -0.14
    ìłĢ
    -0.14
    iminal
    -0.14
    iek
    -0.13
    .arm
    -0.13
    POSITIVE LOGITS
    CMP
    0.16
    ään
    0.15
    illo
    0.15
    _launcher
    0.15
    .nano
    0.15
     Favor
    0.14
    ajas
    0.14
    ĮĴ
    0.14
    ernet
    0.14
    esture
    0.14
    Act Density 0.046%

    No Known Activations