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

    Neuronpedia

    INDEX
    Explanations

    statements or quotes regarding rules, authority, regulations, or procedures

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    andise
    -0.67
    ={
    -0.62
    igraph
    -0.62
    ESE
    -0.61
    rence
    -0.61
    scope
    -0.60
    onent
    -0.60
     Deaths
    -0.60
    umbnail
    -0.59
    INST
    -0.59
    POSITIVE LOGITS
     gonna
    1.13
     gotta
    1.12
     been
    1.02
     unclear
    0.97
     got
    0.94
     impossible
    0.90
     gotten
    0.89
     easy
    0.88
     supposed
    0.88
     not
    0.86
    Act Density 8.196%

    No Known Activations