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

    Neuronpedia

    INDEX
    Explanations

    quantitative data related to experimental results and classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OGND
    -0.90
    IsMutable
    -0.84
    脚注の使い方
    -0.76
    存于互联网档案馆
    -0.74
     Theſe
    -0.71
     myſelf
    -0.71
     itſelf
    -0.71
    AddTagHelper
    -0.70
    ſehen
    -0.69
    ðsíða
    -0.69
    POSITIVE LOGITS
     responses
    0.33
    ArgumentParser
    0.30
     inter
    0.29
     por
    0.27
     rés
    0.25
     rel
    0.25
     response
    0.25
    PullParser
    0.24
     member
    0.24
     example
    0.24
    Act Density 0.766%

    No Known Activations