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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating specific scenarios or conditions

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

    specific cases or situations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ðsíða
    -0.55
    ніципалі
    -0.52
    Renew
    -0.49
     increí
    -0.49
    balleur
    -0.49
     abiye
    -0.49
     rafraî
    -0.49
    -0.48
     ✭✭
    -0.48
    HasAnnotation
    -0.48
    POSITIVE LOGITS
     such
    0.46
     stressful
    0.44
     Salem
    0.39
     Manhattan
    0.38
     stress
    0.37
     prone
    0.37
     tiny
    0.36
     London
    0.36
     situations
    0.36
     Mumbai
    0.35
    Act Density 0.019%

    No Known Activations