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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing skepticism or critique regarding opinions and beliefs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pgsql
    -0.16
     Ñĥмов
    -0.14
    üy
    -0.14
     Americas
    -0.14
     Caldwell
    -0.14
    gaben
    -0.14
    Tomorrow
    -0.14
    ágina
    -0.13
     lax
    -0.13
    sburg
    -0.13
    POSITIVE LOGITS
     nowhere
    0.23
     FACT
    0.19
     fact
    0.19
    FACT
    0.18
     again
    0.16
    .learn
    0.16
    fact
    0.16
     hardly
    0.16
     neither
    0.15
    533
    0.15
    Act Density 0.401%

    No Known Activations