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

    Neuronpedia

    INDEX
    Explanations

    punctuations, particularly commas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    InterfaceOrientation
    -0.14
    AreaView
    -0.14
    urm
    -0.14
    ån
    -0.14
    رÙħ
    -0.14
    chants
    -0.14
    IMER
    -0.14
    iento
    -0.13
    داÙħ
    -0.13
     å»
    -0.13
    POSITIVE LOGITS
    oke
    0.16
    coma
    0.16
    ahat
    0.16
    odo
    0.15
     Chall
    0.15
    leme
    0.15
    xAF
    0.15
    оже
    0.14
    ALT
    0.14
    arry
    0.14
    Act Density 0.000%

    No Known Activations