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

    Neuronpedia

    INDEX
    Explanations

    terms related to effects or actions influenced by conditions or states

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    MessageTagHelper
    -0.79
    ValueStyle
    -0.75
    webElementXpaths
    -0.74
     préféré
    -0.68
     åt
    -0.66
     tecnolog
    -0.65
    improved
    -0.65
     itſelf
    -0.65
    曖昧さ回避
    -0.64
     frumos
    -0.64
    POSITIVE LOGITS
     out
    0.48
     absolut
    0.47
     KI
    0.46
    
    0.44
    ($__
    0.43
    BeginContext
    0.43
     hold
    0.42
    בור
    0.42
    él
    0.41
    irvana
    0.41
    Act Density 0.033%

    No Known Activations