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

    Neuronpedia

    INDEX
    Explanations

    terms related to investigations and legal proceedings

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    yip
    -0.80
    BOOK
    -0.79
    DragonMagazine
    -0.74
    æ°
    -0.73
     schizophrenia
    -0.70
     guiActiveUn
    -0.70
     agitation
    -0.68
    duino
    -0.68
    oshenko
    -0.65
     Saras
    -0.64
    POSITIVE LOGITS
    assed
    1.05
    itating
    0.96
    usalem
    0.96
    iday
    0.96
    ixed
    0.94
    itation
    0.93
    umm
    0.89
    iser
    0.88
    esh
    0.87
    iflower
    0.87
    Act Density 7.411%

    No Known Activations