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

    Neuronpedia

    INDEX
    Explanations

    instances of legal and criminal activities or discussions around rights and accusations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    abad
    -0.61
    ELL
    -0.59
    cell
    -0.58
    NOR
    -0.55
    din
    -0.52
    liam
    -0.51
    entry
    -0.51
    opter
    -0.50
    Boo
    -0.50
    byter
    -0.49
    POSITIVE LOGITS
     thereof
    1.15
     of
    1.10
    Of
    1.01
     Of
    0.97
    of
    0.97
    isance
    0.83
     OF
    0.81
    oft
    0.78
    luster
    0.77
    ados
    0.73
    Act Density 1.509%

    No Known Activations