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

    Neuronpedia

    INDEX
    Explanations

    declarative statements conveying certainty or opinions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.01
    1:0.01
    2:0.10
    3:0.08
    4:0.05
    5:0.02
    6:0.02
    7:0.44
    8:0.03
    9:0.03
    10:0.06
    11:0.09
    Negative Logits
    ebook
    -1.63
    anza
    -1.56
    ulia
    -1.56
    utterstock
    -1.52
    urat
    -1.41
     hijacked
    -1.36
     microscope
    -1.35
     laund
    -1.34
     smugglers
    -1.33
    library
    -1.30
    POSITIVE LOGITS
     Goodbye
    1.69
     brav
    1.55
    ±
    1.49
    atoon
    1.49
    """
    1.49
    rity
    1.46
     goodbye
    1.43
     Thank
    1.33
     sincerity
    1.32
     advis
    1.32
    Act Density 0.007%

    No Known Activations