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

    Neuronpedia

    INDEX
    Explanations

    references to time durations and reading lengths

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    meric
    -0.16
    felt
    -0.15
    ALS
    -0.14
    kara
    -0.14
    iphy
    -0.14
    hazi
    -0.14
    oultry
    -0.14
    opo
    -0.14
    ston
    -0.13
    216
    -0.13
    POSITIVE LOGITS
     read
    0.25
     ago
    0.24
    读
    0.20
     reading
    0.20
    ago
    0.20
     reads
    0.19
    -read
    0.19
    reads
    0.17
     걸
    0.16
    riott
    0.16
    Act Density 0.015%

    No Known Activations