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

    Neuronpedia

    INDEX
    Explanations

    specific numeric values and model references in coding contexts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     ModelExpression
    -0.83
     kasarigan
    -0.82
     Administrativna
    -0.73
    twimg
    -0.72
     houſe
    -0.66
    }]
    -0.65
     pleaſure
    -0.65
     Wikimédia
    -0.65
    Demografie
    -0.63
    "]);
    -0.63
    POSITIVE LOGITS
    rungsseite
    0.58
    DialogTitle
    0.54
    LikeLiked
    0.53
    TypedDataSet
    0.51
     his
    0.46
    dersfield
    0.45
     JMenuItem
    0.45
    …
    0.45
    цездатний
    0.44
    quise
    0.44
    Act Density 0.009%

    No Known Activations