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

    Neuronpedia

    INDEX
    Explanations

    the specific word "irt" with varying degrees of emphasis

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "virtue" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ILCS
    -0.68
     reckoning
    -0.67
    interrupted
    -0.67
    ŃĶ
    -0.62
    cffffcc
    -0.62
    ¬¼
    -0.62
    ULT
    -0.61
    ©¶æ
    -0.59
    sych
    -0.59
    living
    -0.59
    POSITIVE LOGITS
    ually
    0.96
    entials
    0.96
    alia
    0.90
    ilde
    0.89
    inyl
    0.86
    ables
    0.82
    ieth
    0.82
    ullah
    0.80
    igue
    0.79
    ilda
    0.78
    Act Density 0.025%

    No Known Activations