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

    Neuronpedia

    INDEX
    Explanations

    statistics and numerical data related to various topics

    oai_token-act-pair · gpt-3.5-turbo

    numerical statistics and percentages related to survey data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Reviewer
    -0.73
    oeuv
    -0.71
    ipment
    -0.70
    ilic
    -0.69
    aviour
    -0.68
    Orig
    -0.67
    utor
    -0.66
    çīĪ
    -0.66
    actic
    -0.65
    agents
    -0.65
    POSITIVE LOGITS
     percent
    1.13
    %
    1.07
    %,
    1.00
    %"
    0.99
    %.
    0.98
     consecutive
    0.94
     trillion
    0.94
     billion
    0.91
     million
    0.90
     months
    0.89
    Act Density 0.438%

    No Known Activations