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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "hear" and its variants, indicating a focus on listening or obtaining information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hread
    -0.18
    owa
    -0.18
    ito
    -0.16
    oodles
    -0.15
    ugh
    -0.15
    enta
    -0.14
    ced
    -0.14
    AWN
    -0.14
    Ãł
    -0.14
    wide
    -0.13
    POSITIVE LOGITS
    kening
    0.20
    /sm
    0.17
    /watch
    0.17
    itan
    0.17
    712
    0.15
    /read
    0.15
    ald
    0.15
    RowAt
    0.15
    vetica
    0.15
    IDI
    0.15
    Act Density 0.027%

    No Known Activations