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

    Neuronpedia

    INDEX
    Explanations

    references to detailed and comprehensive information or analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    1
    -0.49
    ে
    -0.47
    t
    -0.46
    z
    -0.44
     Gerv
    -0.44
     pop
    -0.44
    e
    -0.43
    tfrac
    -0.43
    мол
    -0.43
     emulsions
    -0.42
    POSITIVE LOGITS
    Extensive
    1.53
     extensive
    1.50
    extensive
    1.46
     comprehensive
    1.45
     detailed
    1.45
     Extensive
    1.45
    Comprehensive
    1.35
    comprehensive
    1.35
    detailed
    1.32
     thorough
    1.32
    Act Density 0.255%

    No Known Activations