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

    Neuronpedia

    INDEX
    Explanations

    superlative forms and phrases indicating comparison or dominance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ùĩد
    -0.17
    resco
    -0.16
    orie
    -0.15
     Henderson
    -0.15
    _buckets
    -0.14
    .opens
    -0.14
     Jim
    -0.14
    hoe
    -0.14
    ÃŃd
    -0.14
    keh
    -0.14
    POSITIVE LOGITS
    iez
    0.16
    anou
    0.15
    bens
    0.15
    eken
    0.14
     trap
    0.14
     å£
    0.14
    æĶ¯
    0.14
    оÑģÑĤаÑĤ
    0.14
    ABCDEFGHIJKLMNOP
    0.13
    íĢ
    0.13
    Act Density 0.000%

    No Known Activations