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

    Neuronpedia

    INDEX
    Explanations

    dates in various formats

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "with."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kind
    -0.66
    hood
    -0.65
    fair
    -0.65
    sov
    -0.64
    chuk
    -0.64
    handler
    -0.63
    mart
    -0.63
    strap
    -0.62
    process
    -0.62
    cemic
    -0.61
    POSITIVE LOGITS
     regards
    1.37
     regard
    1.27
    draw
    1.18
    stood
    1.17
     impunity
    1.10
    standing
    1.06
    drawn
    1.04
     respect
    0.99
    holding
    0.89
    è£ħ
    0.83
    Act Density 0.220%

    No Known Activations