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

    Neuronpedia

    INDEX
    Explanations

    hyphenated words or phrases

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     vel
    -0.71
     Galile
    -0.67
     ESC
    -0.66
    nesday
    -0.64
     Rodrigo
    -0.64
     Patron
    -0.63
     steam
    -0.61
     Kong
    -0.60
     Vive
    -0.60
    isconsin
    -0.60
    POSITIVE LOGITS
    conscious
    1.06
    appropriate
    1.04
    based
    1.03
    specific
    1.02
    wise
    1.00
    checking
    0.96
    changing
    0.96
    filled
    0.94
    sensitive
    0.93
    Specific
    0.92
    Act Density 0.081%

    No Known Activations