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

    Neuronpedia

    INDEX
    Explanations

    verbs related to destruction or disruption

    oai_token-act-pair · gpt-3.5-turbo

    words associated with chaos and disruption

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ©¶æ
    -0.90
    dinand
    -0.74
    ritical
    -0.68
    abet
    -0.67
    sch
    -0.66
    Ń·
    -0.65
    leans
    -0.61
    rawling
    -0.60
     Skydragon
    -0.60
    aza
    -0.60
    POSITIVE LOGITS
    interstitial
    0.79
    nces
    0.78
     havoc
    0.77
    hazard
    0.71
    Tea
    0.70
    ModLoader
    0.69
    Cu
    0.68
    dash
    0.68
    Privacy
    0.68
    ãĥĨãĤ£
    0.66
    Act Density 0.127%

    No Known Activations