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

    Neuronpedia

    INDEX
    Explanations

    references to mathematical or variable expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    x
    -0.20
    t
    -0.18
    y
    -0.17
    lier
    -0.17
    agne
    -0.17
    XML
    -0.17
    b
    -0.17
    c
    -0.17
    i
    -0.16
    atics
    -0.15
    POSITIVE LOGITS
    avier
    0.32
    -ray
    0.27
    ,y
    0.26
    lsx
    0.26
    /y
    0.26
    iaomi
    0.24
    mas
    0.23
    anax
    0.22
    86
    0.22
    anth
    0.22
    Act Density 0.092%

    No Known Activations