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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating procedural steps or instructions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    olumn
    -0.14
    elerik
    -0.14
    entially
    -0.14
    ÃŃsto
    -0.14
     underlying
    -0.14
    woord
    -0.14
    OLON
    -0.14
    ĥĿ
    -0.14
    .matmul
    -0.13
     Charl
    -0.13
    POSITIVE LOGITS
     Lore
    0.15
    orie
    0.15
    -www
    0.15
    ivable
    0.14
    sWith
    0.14
    orne
    0.14
    073
    0.14
    iazza
    0.14
     next
    0.13
    .valueOf
    0.13
    Act Density 0.106%

    No Known Activations