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

    Neuronpedia

    INDEX
    Explanations

    responses indicating correctness or accuracy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    adjective 'correct'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     informée
    -0.42
    VersionUID
    -0.38
    mbi
    -0.38
     Zend
    -0.36
    quins
    -0.36
    śle
    -0.36
     subsystem
    -0.36
    atamente
    -0.35
     subsystems
    -0.35
    buri
    -0.34
    POSITIVE LOGITS
    Correct
    1.63
     Correct
    1.53
    correct
    1.49
     correct
    1.30
     CORRECT
    1.30
    CORRECT
    1.27
     corect
    1.03
     correcto
    0.98
     correcta
    0.93
    incorrect
    0.91
    Act Density 0.011%

    No Known Activations