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

    Neuronpedia

    INDEX
    Explanations

    phrases related to physical activities or tasks

    oai_token-act-pair · gpt-3.5-turbo

    repeated conjunctions and connectors indicating continuity or relation in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ®
    -0.68
    .*
    -0.67
    panel
    -0.65
    NULL
    -0.64
    !:
    -0.64
    Card
    -0.63
    ential
    -0.62
    Fed
    -0.61
     ("
    -0.60
    Adds
    -0.59
    POSITIVE LOGITS
    romeda
    1.07
     blah
    0.95
     stuff
    0.93
     THEN
    0.91
     yeah
    0.91
     secondly
    0.87
     maybe
    0.87
     everybody
    0.86
     thats
    0.86
     hopefully
    0.85
    Act Density 0.409%

    No Known Activations