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

    Neuronpedia

    INDEX
    Explanations

    references to leaving a position or place

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "the" in various contexts related to positions or locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    GW
    -0.75
    MN
    -0.71
    fixes
    -0.71
    ML
    -0.70
     Cosponsors
    -0.69
    NESS
    -0.66
    Stats
    -0.65
     Brach
    -0.65
    Rail
    -0.65
    VEL
    -0.63
    POSITIVE LOGITS
     undone
    0.99
     voic
    0.86
     untouched
    0.85
     unfinished
    0.81
     intact
    0.81
     unprotected
    0.78
     unatt
    0.78
     footprints
    0.75
    hyde
    0.74
     vacuum
    0.73
    Act Density 0.131%

    No Known Activations