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

    Neuronpedia

    INDEX
    Explanations

    references to linear concepts, particularly in mathematical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     nonlinear
    -0.20
    amax
    -0.19
    ENTE
    -0.18
    turnstile
    -0.17
    ennis
    -0.16
    ente
    -0.16
    engers
    -0.16
    anela
    -0.16
    yre
    -0.15
     LENG
    -0.15
    POSITIVE LOGITS
    ly
    0.37
    ized
    0.31
    ization
    0.27
    izing
    0.26
    izable
    0.25
    ities
    0.24
    ize
    0.23
    ised
    0.23
    /angular
    0.21
    izes
    0.20
    Act Density 0.012%

    No Known Activations