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

    Neuronpedia

    INDEX
    Explanations

    references to complementarity and associations indicating enhancement or addition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Empires
    -0.69
    cz
    -0.66
    uler
    -0.64
    RANT
    -0.61
    wcs
    -0.61
    cott
    -0.61
    lisher
    -0.60
     Roses
    -0.60
    rants
    -0.59
    rant
    -0.57
    POSITIVE LOGITS
    arity
    1.19
     complement
    1.10
    anza
    0.89
    atively
    0.84
    ifully
    0.84
    ments
    0.83
    oreal
    0.82
    xual
    0.81
    ately
    0.78
    atives
    0.76
    Act Density 0.015%

    No Known Activations