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

    Neuronpedia

    INDEX
    Explanations

    references to societal progress and achievements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Fol
    -0.14
    éĽĦ
    -0.14
    eree
    -0.13
    Enumerator
    -0.13
    मà¤ķ
    -0.13
    erring
    -0.13
    apt
    -0.13
    owing
    -0.13
    ay
    -0.13
    alice
    -0.13
    POSITIVE LOGITS
     respective
    0.23
     each
    0.20
    each
    0.20
     respectively
    0.20
    .each
    0.17
    lando
    0.16
     sometimes
    0.16
     Each
    0.16
    alat
    0.15
     often
    0.15
    Act Density 0.663%

    No Known Activations