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

    Neuronpedia

    INDEX
    Explanations

    terms related to conversion or transformations in processes

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     transition
    -0.80
    ="'.$
    -0.77
     transitioned
    -0.71
    ",$
    -0.69
     transitioning
    -0.69
     transformation
    -0.68
    "=>$
    -0.68
    ='".$
    -0.68
     FontWeight
    -0.67
    transition
    -0.65
    POSITIVE LOGITS
    CloseOperation
    0.86
     Conversions
    0.81
    NewUrlParser
    0.79
     Converter
    0.78
    mobileqq
    0.77
    Converter
    0.76
     Converts
    0.74
    ecma
    0.73
     conversions
    0.73
    gnore
    0.73
    Act Density 0.019%

    No Known Activations