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

    Neuronpedia

    INDEX
    Explanations

    HTML anchor tags

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    aarrggbb
    -0.50
     (
    -0.46
    ↵
    -0.45
    ot
    -0.44
     In
    -0.44
     to
    -0.43
    ↵↵
    -0.43
     Interess
    -0.43
    маг
    -0.42
    sy
    -0.41
    POSITIVE LOGITS
    abestanden
    0.81
     Roskov
    0.81
     $_"
    0.80
     poffible
    0.79
     Wikimedijinoj
    0.77
     ſmall
    0.77
     themſelves
    0.76
     Anſ
    0.75
     fubject
    0.75
     pleaſure
    0.74
    Act Density 0.004%

    No Known Activations