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

    Neuronpedia

    INDEX
    Explanations

    attends to tokens labeled as "href" from arbitrary script-related tokens

    oai_attention-head · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.09
    1:0.10
    2:0.08
    3:0.14
    4:0.18
    5:0.10
    6:0.19
    7:0.09
    Negative Logits
    }');
    -0.25
    aites
    -0.25
    CMC
    -0.25
    publicain
    -0.24
     bouteille
    -0.24
     betrokken
    -0.24
    setVerticalGroup
    -0.24
     betrek
    -0.24
     tra
    -0.24
     komis
    -0.23
    POSITIVE LOGITS
    ViewFeatures
    0.46
    parsedMessage
    0.43
    DeleteBehavior
    0.38
    InstrumentedTest
    0.36
    enumii
    0.35
    AsUp
    0.35
    /*---
    0.34
    ✨:
    0.34
     ostavi
    0.33
    +:+
    0.33
    Act Density 0.000%

    No Known Activations