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

    Neuronpedia

    INDEX
    Explanations

    comparative phrases indicating a higher degree or intensity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eyim
    -0.17
    oord
    -0.15
    .SIG
    -0.15
    .scalablytyped
    -0.14
    ityEngine
    -0.14
    å½±
    -0.14
    ATRIX
    -0.14
    omi
    -0.14
    AINS
    -0.14
    ÑĤен
    -0.14
    POSITIVE LOGITS
    lund
    0.16
    aravel
    0.15
    icut
    0.15
    tank
    0.14
    icina
    0.14
    toa
    0.14
     SIL
    0.14
    aise
    0.14
    _bd
    0.14
     Voyager
    0.14
    Act Density 0.023%

    No Known Activations