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

    Neuronpedia

    INDEX
    Explanations

    references to linear equations and concepts related to linearity in mathematical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    amax
    -0.20
    engers
    -0.17
     LENG
    -0.16
    ENTE
    -0.15
    лив
    -0.15
    tega
    -0.15
    ender
    -0.15
    ersen
    -0.14
    иÑĢов
    -0.14
    esen
    -0.14
    POSITIVE LOGITS
    ly
    0.38
    ized
    0.30
    izing
    0.27
    ization
    0.27
    ities
    0.24
    izable
    0.24
    ize
    0.24
    coln
    0.23
    ised
    0.22
    -linear
    0.20
    Act Density 0.012%

    No Known Activations