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

    Neuronpedia

    INDEX
    Explanations

    abbreviations or acronyms related to a specific topic

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific resolution or commitment related to "CR"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lies
    -0.81
     Ukrainian
    -0.77
    chest
    -0.74
    lihood
    -0.74
    chuk
    -0.73
     Ukrain
    -0.72
    stra
    -0.71
     Filipino
    -0.71
    les
    -0.71
     Nigerian
    -0.70
    POSITIVE LOGITS
    udence
    1.01
    ACK
    0.94
    EDIT
    0.89
    OSS
    0.85
    isco
    0.84
    ursor
    0.79
    ASH
    0.79
    ouble
    0.79
    ashed
    0.77
    ISIS
    0.77
    Act Density 0.004%

    No Known Activations