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

    Neuronpedia

    INDEX
    Explanations

    references to specific aspects of existence and their implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    TagMode
    -0.67
    <bos>
    -0.53
    OpenHelper
    -0.51
    setcounter
    -0.51
    centerY
    -0.49
    LabelTagHelper
    -0.49
     jäl
    -0.47
     jüng
    -0.46
    genen
    -0.45
    ద్య
    -0.43
    POSITIVE LOGITS
     things
    1.47
     Things
    1.31
    Things
    1.28
    things
    1.23
     THINGS
    1.22
     thing
    1.18
    THINGS
    1.12
     anything
    1.08
     stuff
    1.07
     coisas
    1.06
    Act Density 0.195%

    No Known Activations