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

    Neuronpedia

    INDEX
    Explanations

    certain conjunctions and phrases indicating options, conditions, and contrasts

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

    an island, still retains, allows access

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MemoryWarning
    -0.63
    клопе
    -0.54
     فريبيس
    -0.51
    ActionCreators
    -0.50
    Personendaten
    -0.49
    الحياه
    -0.47
    ConstraintMaker
    -0.47
    OGND
    -0.46
    HasAnnotation
    -0.44
    +#+
    -0.43
    POSITIVE LOGITS
    sunshine
    0.37
    Sunshine
    0.36
     Sunshine
    0.35
     instead
    0.35
     slashing
    0.34
     thither
    0.34
    шру
    0.33
    lifetime
    0.33
     зато
    0.33
     Singing
    0.33
    Act Density 0.041%

    No Known Activations