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

    Neuronpedia

    INDEX
    Explanations

    terms related to linear equations and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    amax
    -0.20
    amac
    -0.15
    лив
    -0.15
    engers
    -0.14
    esen
    -0.14
    ek
    -0.14
    ниÑĩеÑģ
    -0.14
    _UNUSED
    -0.13
    alist
    -0.13
    tega
    -0.13
    POSITIVE LOGITS
    ized
    0.26
    ly
    0.23
    izable
    0.22
    izing
    0.22
    ities
    0.21
    ization
    0.20
    -linear
    0.20
    ize
    0.18
    /qu
    0.17
    ised
    0.16
    Act Density 0.021%

    No Known Activations