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

    Neuronpedia

    INDEX
    Explanations

    phrases related to modifications or alterations

    oai_token-act-pair · gpt-3.5-turbo

    references to organic and sustainable practices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Skydragon
    -0.78
     Torrent
    -0.78
     bells
    -0.76
     Jericho
    -0.76
     Howe
    -0.75
     Jackets
    -0.74
     Bomber
    -0.74
     dots
    -0.73
     Slip
    -0.72
     circle
    -0.71
    POSITIVE LOGITS
    generated
    1.42
    appointed
    1.42
    produced
    1.40
    installed
    1.40
    assembled
    1.38
    selected
    1.36
    elected
    1.35
    protected
    1.35
    charged
    1.34
    designed
    1.34
    Act Density 0.035%

    No Known Activations