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

    Neuronpedia

    INDEX
    Explanations

    comparative language emphasizing uniqueness or distinction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ugas
    -0.19
    iaz
    -0.16
    ека
    -0.16
     Beyond
    -0.15
    heimer
    -0.15
    ello
    -0.14
    çĿ
    -0.14
    liable
    -0.14
    OP
    -0.14
    ando
    -0.14
    POSITIVE LOGITS
     other
    0.24
     single
    0.22
     others
    0.21
     SINGLE
    0.19
    others
    0.19
    other
    0.18
    åħ¶ä»ĸ
    0.18
    single
    0.18
     otras
    0.17
    -single
    0.17
    Act Density 0.055%

    No Known Activations