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

    Neuronpedia

    INDEX
    Explanations

    character names or titles that could potentially be associated with a fictional narrative or storyline

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    cffffcc
    -0.66
    awar
    -0.65
    circ
    -0.56
    ties
    -0.49
     Fault
    -0.49
    dos
    -0.49
    anooga
    -0.49
     Chronicle
    -0.49
    izoph
    -0.48
    piece
    -0.48
    POSITIVE LOGITS
    vironment
    0.80
    zes
    0.68
    itri
    0.67
    xual
    0.63
    stal
    0.61
    jen
    0.60
    leck
    0.60
    bol
    0.60
    ende
    0.58
    chn
    0.58
    Act Density 9.611%

    No Known Activations