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

    Neuronpedia

    INDEX
    Explanations

    proper nouns

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "erg," which appears to be a key term or unit related to the context of the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    İĭ
    -0.79
     Fram
    -0.75
     Mub
    -0.69
    ften
    -0.64
    ģĸ
    -0.63
     Mi
    -0.62
     Promise
    -0.62
    ©¶æ¥µ
    -0.61
     heart
    -0.58
    ĸļ
    -0.58
    POSITIVE LOGITS
    ERG
    0.96
    andom
    0.91
    ling
    0.90
    erg
    0.90
    ener
    0.88
    lings
    0.87
    onom
    0.87
    onomic
    0.87
    ogl
    0.86
    iott
    0.84
    Act Density 0.009%

    No Known Activations