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

    Neuronpedia

    INDEX
    Explanations

    combinations of numbers and specific characters

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks and special characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bered
    -0.69
    SPONSORED
    -0.68
    .}
    -0.67
    î
    -0.66
     todd
    -0.64
    âĢķ
    -0.63
    alore
    -0.62
    reon
    -0.61
     suspic
    -0.61
    rael
    -0.60
    POSITIVE LOGITS
     Allows
    1.51
     Provides
    1.38
     Each
    1.38
     Increases
    1.35
     Adds
    1.33
     Similar
    1.32
     Used
    1.30
     Having
    1.29
     Depending
    1.29
     Contains
    1.28
    Act Density 0.200%

    No Known Activations