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

    Neuronpedia

    INDEX
    Explanations

    references to categories, types, or classifications of items and evidence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     '&#
    -0.15
    æ§
    -0.15
    ades
    -0.15
    lil
    -0.14
    awa
    -0.13
    amel
    -0.13
    aviest
    -0.13
    omi
    -0.13
    ami
    -0.13
    ž
    -0.13
    POSITIVE LOGITS
     besides
    0.26
     than
    0.21
    -than
    0.20
    than
    0.20
    world
    0.19
     niż
    0.18
    bes
    0.17
     equally
    0.17
    _than
    0.17
    Bes
    0.16
    Act Density 0.238%

    No Known Activations