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

    Neuronpedia

    INDEX
    Explanations

    references to personal relationships or friendships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.08
    1:0.08
    2:0.09
    3:0.09
    4:0.08
    5:0.06
    6:0.07
    7:0.08
    8:0.07
    9:0.09
    10:0.09
    11:0.08
    Negative Logits
     dyn
    -2.88
     submar
    -2.77
     mang
    -2.66
    metic
    -2.65
    redo
    -2.65
     prote
    -2.61
    mortem
    -2.55
    monary
    -2.54
    ounty
    -2.53
    metics
    -2.47
    POSITIVE LOGITS
     Gunn
    2.53
     HB
    2.52
     UT
    2.43
     Alt
    2.37
     Tap
    2.36
    dayName
    2.34
     Caption
    2.33
     Brach
    2.33
    psc
    2.31
     OPT
    2.31
    Act Density 0.000%

    No Known Activations