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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating possibilities or speculation

    oai_token-act-pair · gpt-3.5-turbo

    modal verbs indicating uncertainty or possibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Toro
    -0.67
     Patty
    -0.65
     loved
    -0.64
     Sunshine
    -0.64
     Tome
    -0.63
     Viz
    -0.62
    OLD
    -0.61
     Fare
    -0.61
     Winged
    -0.60
    athing
    -0.59
    POSITIVE LOGITS
     occur
    1.44
     signify
    1.26
     preclude
    1.22
     imply
    1.22
     indicate
    1.22
     originate
    1.19
     contam
    1.17
     arise
    1.17
     correlate
    1.17
     affect
    1.16
    Act Density 0.187%

    No Known Activations