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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols and operations related to functions and transformations

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     programs
    -0.56
     program
    -0.54
    openConnection
    -0.52
    WriteTagHelper
    -0.51
    programs
    -0.50
    Попис
    -0.50
     мәкал
    -0.49
    IVEREF
    -0.48
     myö
    -0.47
     process
    -0.46
    POSITIVE LOGITS
    :+:
    0.73
     nakalista
    0.72
     autorytatywna
    0.70
    nodoc
    0.68
     مرئيه
    0.66
    0.66
     surla
    0.66
    ])).
    0.63
    behaviour
    0.62
     noqa
    0.61
    Act Density 0.081%

    No Known Activations