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

    Neuronpedia

    INDEX
    Explanations

    words related to science fiction

    oai_token-act-pair · gpt-3.5-turbo

    references to science fiction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Gates
    -0.75
     Silk
    -0.70
     Illum
    -0.70
     Lawn
    -0.67
    iage
    -0.67
     Balls
    -0.66
     Deer
    -0.65
     Dign
    -0.64
     Swordsman
    -0.64
     Chains
    -0.64
    POSITIVE LOGITS
    repeat
    0.96
    inspired
    0.93
    export
    0.92
    sci
    0.91
    aware
    0.85
    related
    0.85
    induced
    0.85
    dem
    0.84
    interstitial
    0.84
    oriented
    0.84
    Act Density 0.055%

    No Known Activations