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

    Neuronpedia

    INDEX
    Explanations

    terms related to logic, classification systems, and categorization processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    istrovstvÃŃ
    -0.18
    ventory
    -0.17
    ikut
    -0.15
    adder
    -0.15
    ê»
    -0.15
    ãĥ³ãĥ
    -0.15
    ois
    -0.14
     ALT
    -0.14
    ffffffff
    -0.14
    adratic
    -0.14
    POSITIVE LOGITS
    ihn
    0.16
    ÑĩаÑĤ
    0.15
    etri
    0.14
    illac
    0.14
    ÙĪÙĤ
    0.13
    lası
    0.13
    inea
    0.13
     steward
    0.13
    emes
    0.13
     patch
    0.13
    Act Density 0.058%

    No Known Activations