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

    Neuronpedia

    INDEX
    Explanations

    references to duality or pairs in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Various
    -0.15
    åIJĦç§į
    -0.15
    ught
    -0.15
    vb
    -0.15
     various
    -0.14
    box
    -0.14
     ones
    -0.14
    _rsa
    -0.14
    iously
    -0.14
    Various
    -0.14
    POSITIVE LOGITS
     sides
    0.39
    /all
    0.31
     sexes
    0.29
     kinds
    0.27
     sets
    0.26
     halves
    0.26
     ends
    0.24
     parties
    0.24
     types
    0.21
    -sided
    0.20
    Act Density 0.060%

    No Known Activations