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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "When."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    jit
    -0.15
    ena
    -0.15
    iloc
    -0.15
    ýt
    -0.15
    oure
    -0.14
    .batch
    -0.14
    Ä°K
    -0.13
    ect
    -0.13
    achi
    -0.13
    imed
    -0.13
    POSITIVE LOGITS
     asked
    0.29
    ask
    0.22
     word
    0.20
     Asked
    0.19
     did
    0.19
     thinking
    0.18
     eventually
    0.18
     talk
    0.18
     looked
    0.18
     originally
    0.18
    Act Density 0.060%

    No Known Activations