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

    Neuronpedia

    INDEX
    Explanations

    expressions related to complexity and scientific concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    veau
    -0.15
     Cypress
    -0.14
    -prepend
    -0.14
    irtschaft
    -0.14
    cctor
    -0.13
     Emblem
    -0.13
    elo
    -0.13
    åĩĢ
    -0.13
     INCIDENT
    -0.13
    ipar
    -0.13
    POSITIVE LOGITS
     modal
    0.21
    modal
    0.20
     Davidson
    0.19
    Modal
    0.19
     Mein
    0.18
     Modal
    0.18
     Lewis
    0.18
     truth
    0.17
     indispens
    0.17
     intentional
    0.17
    Act Density 0.008%

    No Known Activations