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

    Neuronpedia

    INDEX
    Explanations

    expressions related to seeking help, advice, or guidance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    PerformLayout
    -0.90
    DoubleQuotes
    -0.75
     bezeichneter
    -0.72
     estimés
    -0.72
    TypedDataSet
    -0.69
     Chwiliwch
    -0.68
     CreateTagHelper
    -0.68
     مشين
    -0.68
    preter
    -0.67
     poveznice
    -0.67
    POSITIVE LOGITS
     who
    1.10
     whom
    0.76
    who
    0.73
     Who
    0.70
     którzy
    0.66
     quienes
    0.65
    whom
    0.63
     kdo
    0.62
    Who
    0.59
     kteří
    0.59
    Act Density 0.350%

    No Known Activations