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

    Neuronpedia

    INDEX
    Explanations

    words related to the judicial/criminal process and technical specifications

    oai_token-act-pair · gpt-3.5-turbo

    terms related to processes and their complexities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cipled
    -0.68
     Opportun
    -0.63
    itech
    -0.62
    apego
    -0.61
    recated
    -0.61
    itialized
    -0.60
    ahoo
    -0.59
    partisan
    -0.58
    ookie
    -0.57
    é£
    -0.57
    POSITIVE LOGITS
     itself
    0.96
     varies
    0.91
     versus
    0.90
     depends
    0.88
     depended
    0.83
     compared
    0.83
     vary
    0.79
     beforehand
    0.77
     multiplied
    0.77
     relative
    0.77
    Act Density 0.395%

    No Known Activations