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

    Neuronpedia

    INDEX
    Explanations

    phrases related to software features or updates

    oai_token-act-pair · gpt-3.5-turbo

    references to features and functionalities, particularly in the context of gaming or technology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Lac
    -0.73
    "]=>
    -0.63
    ourt
    -0.60
     Wage
    -0.60
     Capacity
    -0.59
    abama
    -0.58
     Fill
    -0.57
     Saud
    -0.56
     Simulator
    -0.56
     Sons
    -0.56
    POSITIVE LOGITS
     obscure
    1.15
     overlooked
    1.10
     unfamiliar
    1.07
     unexpected
    1.05
     unrelated
    1.05
     unforeseen
    1.04
     unpopular
    1.04
     irrelevant
    0.99
     disliked
    0.98
     inconvenient
    0.97
    Act Density 1.166%

    No Known Activations