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

    Neuronpedia

    INDEX
    Explanations

    phrases related to comparisons or contrasts

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating durations or time intervals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     butterflies
    -0.76
     lifes
    -0.76
     advoc
    -0.73
    ĵĺ
    -0.72
    rons
    -0.72
     strugg
    -0.70
    ¬¼
    -0.70
     cons
    -0.69
    ysis
    -0.69
     basil
    -0.68
    POSITIVE LOGITS
    _-
    0.89
    gpu
    0.79
    SOURCE
    0.76
    âĸº
    0.74
    /-
    0.73
    [[
    0.72
    yes
    0.72
    ->
    0.71
    BUT
    0.71
    why
    0.70
    Act Density 0.037%

    No Known Activations