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

    Neuronpedia

    INDEX
    Explanations

    verbs related to cutting or destroying

    oai_token-act-pair · gpt-3.5-turbo

    words related to significant changes or reductions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    soDeliveryDate
    -0.80
    wcsstore
    -0.70
    Craft
    -0.67
    Recommend
    -0.67
    Import
    -0.66
    ãĤ´ãĥ³
    -0.65
    Streamer
    -0.65
    Fact
    -0.64
    Activity
    -0.63
    ellation
    -0.63
    POSITIVE LOGITS
     throats
    0.95
     unsuspecting
    0.86
     hordes
    0.82
     away
    0.78
     nails
    0.74
     carc
    0.74
    Ń·
    0.73
     down
    0.73
     piles
    0.71
     foes
    0.70
    Act Density 0.410%

    No Known Activations