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

    Neuronpedia

    INDEX
    Explanations

    mathematical notation and expressions related to functions and vector spaces

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     **
    -0.18
    ).*
    -0.17
     Herr
    -0.17
    ^K
    -0.16
    è·¡
    -0.16
     âĢł
    -0.16
     clue
    -0.16
     certain
    -0.15
    ÃŃt
    -0.15
     (
    -0.15
    POSITIVE LOGITS
    âĪ
    0.28
    _star
    0.25
     âĪ
    0.23
    -star
    0.22
    зв
    0.21
    ASTER
    0.20
     star
    0.20
    _STAR
    0.20
     stars
    0.20
    Star
    0.20
    Act Density 0.049%

    No Known Activations