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

    Neuronpedia

    INDEX
    Explanations

    dates and time

    oai_token-act-pair · gpt-3.5-turbo

    the presence of sentences or clauses that end with a period

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     performer
    -0.68
     bounded
    -0.68
     safe
    -0.67
     cradle
    -0.66
     proactive
    -0.66
     stray
    -0.65
     exotic
    -0.64
     spectator
    -0.64
     lap
    -0.63
    ophen
    -0.63
    POSITIVE LOGITS
     Additionally
    1.07
    00
    1.04
    sbm
    1.01
     Previously
    0.99
     Also
    0.98
     However
    0.98
     Meanwhile
    0.95
     Otherwise
    0.95
     Furthermore
    0.95
    5
    0.93
    Act Density 0.165%

    No Known Activations