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

    Neuronpedia

    INDEX
    Explanations

    statistical terms and concepts related to comparisons and averages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     purpoſe
    -0.81
    ſelf
    -0.81
     faſt
    -0.81
     متعلقه
    -0.79
    +:+
    -0.76
    tagHelperRunner
    -0.75
    LookAnd
    -0.74
    PreferredItem
    -0.74
    GOTREF
    -0.74
    исленность
    -0.74
    POSITIVE LOGITS
     also
    0.60
     también
    0.58
    Also
    0.57
     aussi
    0.53
    also
    0.52
     ook
    0.51
    LabelTagHelper
    0.51
     ALSO
    0.51
     del
    0.51
     Also
    0.51
    Act Density 0.505%

    No Known Activations