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

    Neuronpedia

    INDEX
    Explanations

    comparative phrases indicating quantity or degree

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    geme
    -0.16
    erset
    -0.15
    itler
    -0.15
    ARGIN
    -0.15
    Ī
    -0.14
    reste
    -0.14
    baÅŁ
    -0.14
    зÑĭ
    -0.14
     erk
    -0.14
    llen
    -0.14
    POSITIVE LOGITS
     ideal
    0.23
     (<
    0.21
     handful
    0.19
    ideal
    0.19
     ever
    0.18
     ideally
    0.18
     expected
    0.18
     half
    0.17
     optimal
    0.17
     stellar
    0.17
    Act Density 0.020%

    No Known Activations