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

    Neuronpedia

    INDEX
    Explanations

    instances of comparative language and the discussion of various opinions or evaluations of things

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    setVerticalGroup
    -0.95
     الحره
    -0.82
     nahilalakip
    -0.79
    parsedMessage
    -0.78
    ]--;
    -0.77
    __":
    -0.74
    Климат
    -0.69
     myſelf
    -0.69
     Majefty
    -0.68
     houſe
    -0.68
    POSITIVE LOGITS
    Educación
    0.48
     patchy
    0.46
     graft
    0.46
     trawl
    0.43
    FormData
    0.42
     OTT
    0.42
     froide
    0.42
    Mods
    0.41
     gorra
    0.41
    politik
    0.40
    Act Density 0.328%

    No Known Activations