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

    Neuronpedia

    INDEX
    Explanations

    certainty and assurance in statements or claims

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     &___
    -0.50
     mukaan
    -0.49
    nocześnie
    -0.48
    IUrlHelper
    -0.47
    valently
    -0.46
     tij
    -0.45
    UnusedPrivate
    -0.42
     supuestamente
    -0.42
    стоян
    -0.42
    どうも
    -0.42
    POSITIVE LOGITS
    MessageTagHelper
    0.71
     surely
    0.70
     AppCompatTheme
    0.67
    */
    0.67
    ReusableCell
    0.65
     habr
    0.65
     probably
    0.60
    Probably
    0.60
     OnInit
    0.59
    المناصب
    0.59
    Act Density 0.391%

    No Known Activations