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

    Neuronpedia

    INDEX
    Explanations

    technical terms and concepts related to software development and functionality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.29
    1:0.03
    2:0.01
    3:0.11
    4:0.05
    5:0.11
    6:0.04
    7:0.03
    8:0.13
    9:0.11
    10:0.02
    11:0.02
    Negative Logits
     Flavoring
    -1.74
     References
    -1.73
     slips
    -1.66
     explanations
    -1.64
    mails
    -1.64
     citations
    -1.63
     galleries
    -1.62
    assies
    -1.60
     recovered
    -1.59
     Including
    -1.58
    POSITIVE LOGITS
    intensity
    1.83
    GMT
    1.65
    peak
    1.64
    oreal
    1.60
    Buff
    1.50
    iannopoulos
    1.49
    mode
    1.45
    MON
    1.44
    hz
    1.44
    NOR
    1.42
    Act Density 0.001%

    No Known Activations