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

    Neuronpedia

    INDEX
    Explanations

    references to specific seasons and episodes of TV shows

    oai_token-act-pair · gpt-3.5-turbo

    mentions of seasons and episodes in television series

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    loads
    -0.83
    arians
    -0.75
    ices
    -0.72
    ledge
    -0.71
    uria
    -0.70
    agy
    -0.70
    entimes
    -0.68
     nods
    -0.67
    agara
    -0.67
    zzle
    -0.66
    POSITIVE LOGITS
     infamous
    0.95
     same
    0.92
     aforementioned
    0.88
     latter
    0.84
     dreaded
    0.81
     famed
    0.77
     upcoming
    0.76
     latest
    0.76
     venerable
    0.73
     defunct
    0.72
    Act Density 0.315%

    No Known Activations