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

    Neuronpedia

    INDEX
    Explanations

    time-related events or actions indicated by the occurrences of 'once' or 'twice'

    oai_token-act-pair · gpt-3.5-turbo

    instances of the number two and phrases indicating duality or a comparison between two entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Pastebin
    -0.72
    paralle
    -0.68
    +.
    -0.66
    vr
    -0.65
    rawdownloadcloneembedreportprint
    -0.65
    much
    -0.62
    kay
    -0.61
    ......
    -0.60
    overs
    -0.60
    .]
    -0.60
    POSITIVE LOGITS
     foreground
    0.67
     sexes
    0.65
     statically
    0.65
    itative
    0.60
     fists
    0.60
     literal
    0.60
     neutral
    0.58
     outright
    0.56
     benevolent
    0.55
     mundane
    0.55
    Act Density 0.302%

    No Known Activations