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

    Neuronpedia

    INDEX
    Explanations

    mentions of numbers related to statistics, such as quantities or figures

    oai_token-act-pair · gpt-3.5-turbo

    the conjunction "and" used frequently, indicating lists or connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    edia
    -0.76
    isco
    -0.65
    NVIDIA
    -0.63
    ESE
    -0.63
    Games
    -0.62
    èª
    -0.62
    POST
    -0.62
    ogy
    -0.60
    um
    -0.60
    ukong
    -0.59
    POSITIVE LOGITS
     assorted
    0.98
     counting
    0.96
     totaling
    0.87
     dozens
    0.82
     countless
    0.77
     six
    0.75
     apiece
    0.75
     untold
    0.74
     equivalents
    0.72
     eight
    0.71
    Act Density 0.214%

    No Known Activations