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

    Neuronpedia

    INDEX
    Explanations

    phrases related to personal experience or letters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.03
    1:0.01
    2:0.07
    3:0.13
    4:0.25
    5:0.02
    6:0.11
    7:0.13
    8:0.04
    9:0.03
    10:0.04
    11:0.08
    Negative Logits
    Rated
    -2.02
     Cosponsors
    -1.74
    redits
    -1.68
    reek
    -1.45
    orrow
    -1.39
    owered
    -1.39
    Tech
    -1.36
    instead
    -1.36
    quickShipAvailable
    -1.35
     =================================
    -1.33
    POSITIVE LOGITS
     caveats
    1.95
     exceptions
    1.87
     occasional
    1.81
     ones
    1.53
     obvious
    1.52
     limitations
    1.50
     nuts
    1.50
     caveat
    1.49
     fluctuations
    1.44
     prohibitions
    1.40
    Act Density 0.005%

    No Known Activations