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

    Neuronpedia

    INDEX
    Explanations

    references to hierarchical structures or components in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uela
    -0.16
    set
    -0.15
    -vous
    -0.14
    heets
    -0.14
    far
    -0.14
    «a
    -0.14
    inkel
    -0.14
    J
    -0.14
    adh
    -0.14
    olds
    -0.14
    POSITIVE LOGITS
    /sub
    0.17
    mers
    0.16
    olor
    0.16
    =sub
    0.16
    erif
    0.15
    divide
    0.15
    klä
    0.14
    atomic
    0.14
    lrt
    0.14
     pháºŃn
    0.14
    Act Density 0.029%

    No Known Activations