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

    Neuronpedia

    INDEX
    Explanations

    instances of puncturing or creating openings in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ettle
    -0.14
    æ¤ħ
    -0.14
    ujÄħ
    -0.14
    ipl
    -0.13
     rack
    -0.13
    ãĥ¼ãĥij
    -0.13
     Couch
    -0.13
     tors
    -0.13
    å·»
    -0.13
    _kelas
    -0.12
    POSITIVE LOGITS
     holes
    0.54
     hole
    0.50
     openings
    0.49
    holes
    0.45
    -hole
    0.42
     Hole
    0.41
    hole
    0.39
     opening
    0.38
     gaps
    0.36
    åŃĶ
    0.36
    Act Density 0.288%

    No Known Activations