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

    Neuronpedia

    INDEX
    Explanations

    references to identity, roles, and classifications of behavior

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     scolas
    -0.64
     educativo
    -0.60
     PublicKey
    -0.57
     bedrijven
    -0.56
    sság
    -0.54
     disambiguazione
    -0.54
     Luglio
    -0.54
     educativas
    -0.54
    vábbi
    -0.53
    ówno
    -0.53
    POSITIVE LOGITS
     genius
    0.68
     optim
    0.67
     extro
    0.63
     hero
    0.62
     person
    0.61
     ***!
    0.59
     weir
    0.59
     idiot
    0.56
     gentleman
    0.56
     nerd
    0.56
    Act Density 0.343%

    No Known Activations