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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing opinions and conjectures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    celik
    -0.15
    ibble
    -0.15
    posium
    -0.14
    chio
    -0.14
    erd
    -0.13
    éĻ¸
    -0.13
    duit
    -0.13
    OfClass
    -0.13
    ATEST
    -0.13
    ysi
    -0.13
    POSITIVE LOGITS
    (!
    0.16
    оÑģÑĤи
    0.15
    (?
    0.15
    uluk
    0.14
    ocz
    0.14
    edral
    0.13
    PointerException
    0.13
    )a
    0.13
     _.
    0.13
    hof
    0.13
    Act Density 0.082%

    No Known Activations