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

    Neuronpedia

    INDEX
    Explanations

    references to specific classifications or categorizations, particularly related to medical or scientific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    c
    -0.35
    m
    -0.32
    ec
    -0.31
    l
    -0.30
    cx
    -0.30
    cc
    -0.29
    a
    -0.28
    cid
    -0.28
    ele
    -0.28
    t
    -0.28
    POSITIVE LOGITS
    fa
    0.20
    fe
    0.20
    fd
    0.20
    fdc
    0.19
    fc
    0.19
    fea
    0.18
    feb
    0.18
    fee
    0.17
    ffe
    0.16
    gie
    0.16
    Act Density 0.009%

    No Known Activations