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

    Neuronpedia

    INDEX
    Explanations

    terms related to established methods or practices

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     series
    -0.45
    bull
    -0.45
    WorkItem
    -0.42
     Series
    -0.41
     bull
    -0.41
     lắm
    -0.40
    bland
    -0.40
     xuyên
    -0.40
     Bull
    -0.40
     follow
    -0.39
    POSITIVE LOGITS
    rungsseite
    0.66
     gjerne
    0.65
     fico
    0.65
     Photocase
    0.64
    +");
    0.63
     interchangeably
    0.63
    verwijspagina
    0.62
     brukar
    0.62
    IBOutlet
    0.61
    \{\\
    0.60
    Act Density 0.099%

    No Known Activations