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

    Neuronpedia

    INDEX
    Explanations

    phrases relating to themes of societal behaviors and expectations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AnimationsModule
    -0.69
    ddots
    -0.65
    amaño
    -0.64
     ostavi
    -0.62
    inaudible
    -0.61
    CROSSTALK
    -0.60
     дописавши
    -0.60
    RectangleBorder
    -0.59
    freopen
    -0.58
    UserScript
    -0.58
    POSITIVE LOGITS
    kosh
    0.54
     slaap
    0.52
     freilich
    0.50
     persino
    0.48
     vervolgens
    0.47
     nocturn
    0.45
     στι
    0.45
     zunächst
    0.44
    richtet
    0.43
     لیے
    0.43
    Act Density 0.777%

    No Known Activations