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
    ena
    -0.15
    ýt
    -0.14
    iry
    -0.14
    -за
    -0.14
    oki
    -0.14
    eries
    -0.13
    ilo
    -0.13
    ematics
    -0.13
    iloc
    -0.13
    ect
    -0.13
    POSITIVE LOGITS
     did
    0.24
     properly
    0.20
     does
    0.19
     asked
    0.18
     done
    0.17
     you
    0.17
     finished
    0.16
    goog
    0.16
     autocomplete
    0.16
    ask
    0.16
    Act Density 0.075%

    No Known Activations