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

    Neuronpedia

    INDEX
    Explanations

    specific occasions or events

    oai_token-act-pair · gpt-3.5-turbo

    references to significant events or occasions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Lock
    -0.69
     sucks
    -0.63
    Mail
    -0.62
    Po
    -0.59
    Tra
    -0.58
    Scan
    -0.56
     Research
    -0.56
    pps
    -0.55
    osh
    -0.55
     Stream
    -0.55
    POSITIVE LOGITS
     occasion
    4.40
     occasions
    2.49
     occas
    1.41
     pretext
    1.18
     occ
    1.16
     circumstance
    1.14
     opportunity
    1.10
     anniversary
    0.99
     purpose
    0.94
     excuse
    0.89
    Act Density 0.005%

    No Known Activations