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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating levels, scales, or magnitudes of various situations or phenomena

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ucher
    -0.17
    weg
    -0.17
    isher
    -0.17
     Barrett
    -0.17
    ENTS
    -0.15
    istra
    -0.15
    ques
    -0.15
    irl
    -0.14
    ector
    -0.14
    *>*
    -0.14
    POSITIVE LOGITS
    font
    0.16
    FONT
    0.14
    UNT
    0.14
    illo
    0.14
     extent
    0.14
    um
    0.14
     amount
    0.14
     RuntimeObject
    0.14
    extent
    0.14
    Ñij
    0.13
    Act Density 0.077%

    No Known Activations