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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate the presence or absence of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eb
    -0.16
    mmas
    -0.15
    awa
    -0.14
    izados
    -0.14
    ximo
    -0.13
    KA
    -0.13
    igo
    -0.13
    /XML
    -0.13
     ç·
    -0.13
    ãĥ³ãĥĦ
    -0.13
    POSITIVE LOGITS
    γει
    0.16
    /is
    0.16
    rone
    0.15
    eyh
    0.15
    ÙĬÙĨÙĩ
    0.14
    /w
    0.14
    _ble
    0.14
    lage
    0.14
    éĩı
    0.13
     relief
    0.13
    Act Density 0.131%

    No Known Activations