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

    Neuronpedia

    INDEX
    Explanations

    explicit references to food

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Following qualifying words, like "sounding" or "be"

    np_acts-logits-general · gemini-2.0-flash

    insincere or exaggerated language

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tahui
    -0.60
     tikra
    -0.53
    pédie
    -0.52
     merve
    -0.49
     lära
    -0.48
     المعيارى
    -0.47
     nakalista
    -0.46
    OCCURRED
    -0.46
     rör
    -0.45
    räck
    -0.45
    POSITIVE LOGITS
     exaggeration
    0.98
     cliché
    0.95
     exaggerating
    0.91
     cliche
    0.91
     clich
    0.80
     sounding
    0.79
     understatement
    0.78
     exaggerate
    0.78
     biased
    0.78
     exagger
    0.78
    Act Density 0.279%

    No Known Activations