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

    Neuronpedia

    INDEX
    Explanations

    names or terms related to individuals or organizations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    raints
    -0.86
    sburgh
    -0.80
    lain
    -0.74
    DERR
    -0.68
     Responsibility
    -0.65
    ModLoader
    -0.65
    ingham
    -0.65
     McDonnell
    -0.64
    raint
    -0.63
    aldehyde
    -0.62
    POSITIVE LOGITS
    venth
    1.57
    phant
    1.26
    fter
    1.00
    ven
    0.95
    ves
    0.88
    oton
    0.86
    ph
    0.85
    ighth
    0.85
    lect
    0.85
    fts
    0.84
    Act Density 0.032%

    No Known Activations