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

    Neuronpedia

    INDEX
    Explanations

    references to guides or instructions on specific cultural practices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    onds
    -0.14
    ATUS
    -0.14
    844
    -0.14
    andle
    -0.14
    adem
    -0.14
     buckets
    -0.13
     spokesman
    -0.13
    ระ
    -0.13
    ANDLE
    -0.13
     arÅŁiv
    -0.13
    POSITIVE LOGITS
     torn
    0.29
     ripped
    0.25
     tore
    0.23
     tear
    0.23
     phot
    0.23
     clipping
    0.22
     stap
    0.22
     tearing
    0.22
     ripping
    0.19
     folded
    0.18
    Act Density 0.073%

    No Known Activations