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

    Neuronpedia

    INDEX
    Explanations

    numeric values and their representations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     <<<<<<<<<<<<<<
    -0.71
    mandu
    -0.69
    adaptiveStyles
    -0.67
    principalColumn
    -0.58
    berdayakan
    -0.58
    elfde
    -0.57
     pungkasnya
    -0.55
    Izvori
    -0.54
     Réponses
    -0.54
    BrowserModule
    -0.54
    POSITIVE LOGITS
    帖最后由
    0.59
     _$
    0.53
    TestBed
    0.52
     للمعارف
    0.51
    Aholisi
    0.49
    elow
    0.47
    }:${
    0.46
     Tucker
    0.45
    kloped
    0.44
     "..\..\..\
    0.44
    Act Density 0.770%

    No Known Activations