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

    Neuronpedia

    INDEX
    Explanations

    concepts related to scientific principles and their significance in understanding complex systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     derivation
    -0.19
    lear
    -0.17
     Valent
    -0.15
    amen
    -0.15
     determination
    -0.15
    actices
    -0.15
    zend
    -0.14
     determin
    -0.14
    426
    -0.13
    ces
    -0.13
    POSITIVE LOGITS
     interesting
    0.20
    interesting
    0.20
    quantity
    0.19
     quantities
    0.19
     physically
    0.18
    Quantity
    0.18
     simpl
    0.18
    Interesting
    0.18
     quantity
    0.17
     Ged
    0.17
    Act Density 0.125%

    No Known Activations