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

    Neuronpedia

    INDEX
    Explanations

    information related to events, incidents, or occurrences

    oai_token-act-pair · gpt-3.5-turbo

    references to specific incidents and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itized
    -0.70
     adop
    -0.69
    outer
    -0.68
    joice
    -0.67
     floats
    -0.67
     wra
    -0.66
    bearing
    -0.63
    Wra
    -0.62
     stripes
    -0.62
    flo
    -0.61
    POSITIVE LOGITS
     Airbus
    0.88
     Beir
    0.78
     Hollande
    0.74
     Bates
    0.74
     Auburn
    0.71
     Corker
    0.69
     Naval
    0.68
    GMT
    0.68
     Bernstein
    0.67
     Siem
    0.67
    Act Density 0.461%

    No Known Activations