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

    Neuronpedia

    INDEX
    Explanations

    words and phrases indicating numerical values or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    GGLE
    -0.15
    asti
    -0.15
    vÄĽ
    -0.14
    /topics
    -0.14
    ncia
    -0.14
    CEED
    -0.13
    icamente
    -0.13
    addtogroup
    -0.13
    _NOP
    -0.13
     Passive
    -0.13
    POSITIVE LOGITS
    ãĥ¼ãĥľ
    0.18
    anja
    0.18
    uida
    0.16
    iten
    0.16
    eger
    0.15
     Cust
    0.15
    ÑĭÑĤ
    0.14
    inda
    0.14
    uez
    0.14
     Cool
    0.14
    Act Density 0.009%

    No Known Activations