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

    Neuronpedia

    INDEX
    Explanations

    words related to quantifiable measurements or boundaries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ont
    -0.14
     ins
    -0.14
    æħ¢
    -0.14
    zen
    -0.14
     interpolate
    -0.14
    less
    -0.13
    ç³»
    -0.13
     sher
    -0.13
    jo
    -0.13
    931
    -0.13
    POSITIVE LOGITS
    ÑĤин
    0.17
    upal
    0.16
     Haz
    0.15
    tem
    0.15
    ãĥ³ãĥī
    0.14
    _managed
    0.14
    anness
    0.14
    DL
    0.14
    caster
    0.14
    ismatic
    0.13
    Act Density 0.008%

    No Known Activations