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

    Neuronpedia

    INDEX
    Explanations

    phrases related to varying quantities or ranges

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    assertSame
    -0.49
     يتيمه
    -0.49
    maketitle
    -0.49
    assertIs
    -0.48
     préférences
    -0.47
     الحره
    -0.47
    urgie
    -0.47
    WriteLiteral
    -0.47
     AssemblyTitle
    -0.46
    hadiran
    -0.46
    POSITIVE LOGITS
    AddTagHelper
    0.75
     Rover
    0.67
     rover
    0.65
    WriteAttribute
    0.64
    finder
    0.63
    内的
    0.61
     couverts
    0.61
     cellpadding
    0.60
    Rover
    0.59
     saites
    0.58
    Act Density 0.199%

    No Known Activations