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

    Neuronpedia

    INDEX
    Explanations

    elements related to formatting and structuring information in texts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Tikang
    -0.51
     مرئيه
    -0.47
    licité
    -0.47
    IndentedString
    -0.46
     azar
    -0.46
     Werbe
    -0.43
    reactstrap
    -0.42
     commissioner
    -0.42
     Commissioner
    -0.41
    carpa
    -0.40
    POSITIVE LOGITS
    INCLUDING
    0.79
     Including
    0.79
    Including
    0.77
    including
    0.74
     including
    0.72
    AutoField
    0.71
     INCLUDING
    0.65
     např
    0.64
    例えば
    0.63
    包括
    0.61
    Act Density 0.377%

    No Known Activations