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

    Neuronpedia

    INDEX
    Explanations

    comparative phrases emphasizing quantities or measures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sta
    -0.15
    529
    -0.15
     Weaver
    -0.15
    oppel
    -0.15
    ³
    -0.14
    lsen
    -0.14
    kowski
    -0.14
     tamp
    -0.14
    anches
    -0.14
    acman
    -0.14
    POSITIVE LOGITS
     enough
    0.20
    ãĥĥãĥĦ
    0.18
    óng
    0.16
    ubb
    0.16
    евеÑĢ
    0.15
    rama
    0.14
    ãĥ¼ãĥľ
    0.14
    'gc
    0.14
    icone
    0.14
    bef
    0.14
    Act Density 0.064%

    No Known Activations