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

    Neuronpedia

    INDEX
    Explanations

    words and phrases that indicate quantification or categorization of entities

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    wiſe
    -0.59
     Means
    -0.57
    Means
    -0.57
     means
    -0.54
    means
    -0.52
    ultuous
    -0.52
    ImageContext
    -0.51
    ējās
    -0.50
     Mox
    -0.50
    folge
    -0.49
    POSITIVE LOGITS
    rungsseite
    0.67
    ViewChild
    0.64
     виправивши
    0.62
     Référence
    0.62
    AxisAlignment
    0.60
     FishBase
    0.59
    findpost
    0.59
     bestand
    0.59
    OGND
    0.58
    rescence
    0.58
    Act Density 0.014%

    No Known Activations