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

    Neuronpedia

    INDEX
    Explanations

    content related to significant scientific data or variables

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Bif
    -0.69
     Tsu
    -0.65
     CWE
    -0.64
    irited
    -0.63
     Italijanski
    -0.62
    witcher
    -0.62
    zyw
    -0.60
     kasarigan
    -0.59
    rester
    -0.59
     buc
    -0.59
    POSITIVE LOGITS
    
    0.88
    
    0.76
    
    0.70
    endregion
    0.69
    المكان
    0.67
    usercontent
    0.65
    ViewFeatures
    0.64
    Cyfeiriadau
    0.62
    "]=
    0.62
    
    0.60
    Act Density 0.000%

    No Known Activations