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

    Neuronpedia

    INDEX
    Explanations

    positive adjectives or phrases indicating quality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Tembelea
    -0.52
    hyrchwyd
    -0.52
    RotationOrder
    -0.46
    GOTREF
    -0.44
     surla
    -0.42
    httphttps
    -0.41
    RTHOOK
    -0.40
    RegistryLite
    -0.38
    uxxxx
    -0.38
     disruptive
    -0.38
    POSITIVE LOGITS
     disambiguazione
    0.50
    SEGUIR
    0.49
     costumbre
    0.48
     feroit
    0.46
     vectorielle
    0.44
     rodríguez
    0.44
     weather
    0.43
     movies
    0.43
     yourself
    0.42
     élect
    0.41
    Act Density 0.259%

    No Known Activations