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

    Neuronpedia

    INDEX
    Explanations

    patterns in the structural formatting of text

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    findpost
    -1.17
     Mard
    -0.78
     AssemblyVersion
    -0.74
    Beh
    -0.72
    RetentionPolicy
    -0.72
     Davi
    -0.71
     Becher
    -0.69
    ]='\
    -0.69
     softener
    -0.69
    __':
    -0.69
    POSITIVE LOGITS
     -------
    1.10
    -------
    1.05
     ------
    0.98
    ------
    0.91
    --------
    0.77
    ly
    0.74
     --------
    0.72
     SOP
    0.69
     Clippers
    0.68
     Keyes
    0.65
    Act Density 0.022%

    No Known Activations