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

    Neuronpedia

    INDEX
    Explanations

    punctuation and numerical patterns in the text

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    principalTable
    -0.68
    rungsseite
    -0.60
     '*':
    -0.53
     vecchia
    -0.52
     sauver
    -0.52
     vieilles
    -0.51
     voient
    -0.50
     riconoscimento
    -0.50
     hini
    -0.50
     pasillo
    -0.49
    POSITIVE LOGITS
     AssemblyCulture
    0.79
    httphttps
    0.77
    +#+
    0.68
    +#+#
    0.65
    Personendaten
    0.62
     iNdEx
    0.57
    })));
    0.56
    tagHelperRunner
    0.54
    endphp
    0.53
    ۣ
    0.52
    Act Density 0.001%

    No Known Activations