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

    Neuronpedia

    INDEX
    Explanations

    mathematical variables and symbols, particularly in equations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Char
    -0.15
    exus
    -0.14
    vida
    -0.14
    icit
    -0.14
    lect
    -0.14
    igit
    -0.13
     Hex
    -0.13
     Cass
    -0.13
     covered
    -0.13
     Beam
    -0.13
    POSITIVE LOGITS
    jis
    0.15
    515
    0.15
    513
    0.14
    apolis
    0.14
    Uid
    0.14
    510
    0.14
    lint
    0.13
    è·³
    0.13
    chal
    0.13
    ruk
    0.13
    Act Density 0.095%

    No Known Activations