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

    Neuronpedia

    INDEX
    Explanations

    mentions related to different types of groups or organizations

    oai_token-act-pair · gpt-3.5-turbo

    terms and phrases related to various communities and organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    amaz
    -0.68
     spills
    -0.65
     overfl
    -0.64
     spilled
    -0.60
     puzz
    -0.58
     therm
    -0.57
     inver
    -0.55
    eatures
    -0.55
     swat
    -0.54
     intermittent
    -0.54
    POSITIVE LOGITS
     someday
    0.90
     anymore
    0.85
     forever
    0.83
    thood
    0.82
    elight
    0.79
     irrespective
    0.77
     ASAP
    0.75
     regardless
    0.75
     without
    0.74
     whilst
    0.73
    Act Density 0.682%

    No Known Activations