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

    Neuronpedia

    INDEX
    Explanations

    mentions of leaving or departing from a place or situation

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to possession or ownership

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    GW
    -0.72
    NESS
    -0.72
    ML
    -0.71
    MN
    -0.70
     Cosponsors
    -0.70
    fixes
    -0.66
     STA
    -0.64
    Stats
    -0.62
    Rail
    -0.61
     Misc
    -0.61
    POSITIVE LOGITS
     undone
    0.96
     untouched
    0.94
     intact
    0.92
     footprints
    0.86
     mark
    0.83
     unatt
    0.82
     voic
    0.81
     unexpl
    0.80
     unprotected
    0.80
     unfinished
    0.79
    Act Density 0.146%

    No Known Activations