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

    Neuronpedia

    INDEX
    Explanations

    references to social media platforms and related actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     esprits
    -0.47
     preuves
    -0.47
     pouvoirs
    -0.46
     presence
    -0.45
     manos
    -0.45
     coordonnées
    -0.43
     Handeln
    -0.42
     symboles
    -0.42
     lecteurs
    -0.42
     Gründe
    -0.42
    POSITIVE LOGITS
     Modal
    0.53
     Princip
    0.48
    Prin
    0.47
     cared
    0.46
     modal
    0.46
    aragus
    0.46
    princip
    0.45
    Mom
    0.44
    Mechan
    0.44
    ]^{-
    0.44
    Act Density 0.113%

    No Known Activations