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

    Neuronpedia

    INDEX
    Explanations

    instances of the greater-than symbol (">")

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     repens
    -0.41
     manufacture
    -0.40
     subject
    -0.40
    exitRule
    -0.40
    ReusableCell
    -0.40
    binaan
    -0.39
     compromise
    -0.39
     escape
    -0.38
    ferro
    -0.37
     irrever
    -0.37
    POSITIVE LOGITS
    GT
    0.76
    gt
    0.75
     struct
    0.75
     GT
    0.68
     gt
    0.66
     Gt
    0.64
     Struct
    0.61
     оригіналу
    0.59
     مشين
    0.58
    Gt
    0.56
    Act Density 0.158%

    No Known Activations