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

    Neuronpedia

    INDEX
    Explanations

    information related to the design and development process of a character or concept

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     fter
    -0.76
     gilet
    -0.69
     hoody
    -0.68
     ecru
    -0.68
     sceptre
    -0.67
    efty
    -0.66
    timately
    -0.66
     unwarran
    -0.65
     sophie
    -0.63
     hairc
    -0.62
    POSITIVE LOGITS
     tré
    0.51
    4
    0.46
    iseta
    0.45
    8
    0.44
    6
    0.44
    7
    0.43
    2
    0.43
    1
    0.43
     obti
    0.42
    3
    0.42
    Act Density 0.055%

    No Known Activations