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

    Neuronpedia

    INDEX
    Explanations

    phrases related to actions and decision-making in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    adlo
    -0.16
    andler
    -0.15
     Clarkson
    -0.15
    èĿ
    -0.15
     addCriterion
    -0.15
    anou
    -0.14
    finder
    -0.14
    mac
    -0.14
    anko
    -0.14
    eline
    -0.13
    POSITIVE LOGITS
     cater
    0.15
    .Override
    0.15
     catering
    0.14
     Trot
    0.14
    oux
    0.14
    ikh
    0.14
    .addObserver
    0.14
     ><?
    0.14
     abstract
    0.14
    coni
    0.14
    Act Density 0.144%

    No Known Activations