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

    Neuronpedia

    INDEX
    Explanations

    mentions of alternatives or choices in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arna
    -0.17
    973
    -0.17
    653
    -0.17
    gaard
    -0.14
    akin
    -0.14
    418
    -0.14
    Initializing
    -0.14
    ναν
    -0.14
    782
    -0.14
    385
    -0.14
    POSITIVE LOGITS
     several
    0.25
     Bust
    0.18
    ific
    0.18
     multiple
    0.18
    ifice
    0.17
     plusieurs
    0.17
    Several
    0.16
    prefer
    0.16
    å¤ļ
    0.16
    eres
    0.16
    Act Density 0.017%

    No Known Activations