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

    Neuronpedia

    INDEX
    Explanations

    dates and their associated events

    oai_token-act-pair · gpt-3.5-turbo

    dates and numerical references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     suite
    -0.74
     abbre
    -0.71
     unit
    -0.63
     distance
    -0.61
     plural
    -0.60
     subsystem
    -0.60
     shrink
    -0.59
     prerequisite
    -0.59
     separ
    -0.58
     cleaner
    -0.58
    POSITIVE LOGITS
    ioxide
    0.69
    Ò
    0.66
    ushima
    0.66
    th
    0.65
    lem
    0.65
    âĸĪ
    0.65
    Thom
    0.64
    âĸĪâĸĪ
    0.64
    aos
    0.64
     Isle
    0.62
    Act Density 0.186%

    No Known Activations