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

    Neuronpedia

    INDEX
    Explanations

    phrases instructing or recommending to check something out

    oai_token-act-pair · gpt-3.5-turbo

    calls to action encouraging the reader to check out content or resources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cius
    -0.69
    staking
    -0.69
    Edited
    -0.67
     withdrawn
    -0.66
    song
    -0.65
    cious
    -0.65
     dictate
    -0.64
     awake
    -0.62
     trem
    -0.62
    ally
    -0.61
    POSITIVE LOGITS
    fitted
    0.84
    neau
    0.75
     whats
    0.72
    posts
    0.70
    reon
    0.70
    nels
    0.70
    rics
    0.69
    rue
    0.68
    racuse
    0.68
    riage
    0.67
    Act Density 0.057%

    No Known Activations