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

    Neuronpedia

    INDEX
    Explanations

    action verbs and phrases related to exploration and discovery

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     recommandons
    -0.60
    SharedDtor
    -0.59
     disambiguazione
    -0.56
     dolayı
    -0.55
    олові
    -0.55
    こち
    -0.53
    ähteet
    -0.53
    StoryboardSegue
    -0.50
     IIRC
    -0.49
     Meilleures
    -0.49
    POSITIVE LOGITS
     who
    1.23
     why
    1.19
     exactly
    1.07
     where
    1.06
     what
    1.04
     how
    0.94
     everything
    0.91
     some
    0.89
    who
    0.87
    exactly
    0.87
    Act Density 0.441%

    No Known Activations