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

    Neuronpedia

    INDEX
    Explanations

    affirmative phrases and expressions indicating certainty or emphasis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eldon
    -0.17
    idd
    -0.16
    thon
    -0.15
     Overnight
    -0.15
    otes
    -0.14
    ote
    -0.14
    IDD
    -0.14
    865
    -0.14
     Williamson
    -0.14
    eros
    -0.13
    POSITIVE LOGITS
     gonna
    0.16
    .datatables
    0.15
    Neutral
    0.15
    æĦŁ
    0.14
    ograd
    0.14
    ovo
    0.14
    NullException
    0.14
     *)((
    0.14
    Å¡ku
    0.13
    ige
    0.13
    Act Density 0.336%

    No Known Activations