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

    Neuronpedia

    INDEX
    Explanations

    peculiar or unusual adjectives describing experiences or phenomena

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    KURZBESCHREIBUNG
    -0.41
    Bakgrunnsstoff
    -0.38
     propOrder
    -0.38
     Houſe
    -0.38
     Superhost
    -0.35
    actéris
    -0.34
     Soccerway
    -0.34
    yelidikan
    -0.34
    Representation
    -0.34
    engeti
    -0.34
    POSITIVE LOGITS
    msgTypes
    0.67
     twist
    0.59
     twists
    0.56
     phenomenon
    0.55
     happenings
    0.55
     coincidence
    0.54
     phenomena
    0.54
     quirks
    0.52
    ball
    0.52
    styleable
    0.52
    Act Density 0.240%

    No Known Activations