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

    Neuronpedia

    INDEX
    Explanations

    questions or phrases related to how something is done or explained

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Very
    -0.66
     Very
    -0.64
     Longer
    -0.62
    Datuak
    -0.60
    "]));
    -0.58
     semakin
    -0.57
    Faster
    -0.56
    Greater
    -0.56
    -0.55
    MigrationBuilder
    -0.55
    POSITIVE LOGITS
     much
    1.15
     strong
    0.99
     powerful
    0.94
     expensive
    0.92
    much
    0.87
     intense
    0.86
     difficult
    0.86
     big
    0.86
     bad
    0.84
     complicated
    0.82
    Act Density 0.415%

    No Known Activations