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

    Neuronpedia

    INDEX
    Explanations

    words that indicate numerical or comparative data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ů
    -0.17
    ãĥ¼ãĥ«
    -0.15
     Gro
    -0.15
    ena
    -0.15
    gro
    -0.14
    isini
    -0.14
    Gro
    -0.14
    iolet
    -0.14
     Usage
    -0.13
    /Peak
    -0.13
    POSITIVE LOGITS
    azu
    0.19
     *)((
    0.17
     Stout
    0.15
    _va
    0.15
     pardon
    0.15
    illow
    0.15
    SCI
    0.14
     Daly
    0.14
    ridged
    0.14
    uben
    0.14
    Act Density 0.003%

    No Known Activations