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

    Neuronpedia

    INDEX
    Explanations

    references to past events or highlights

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.04
    1:0.01
    2:0.12
    3:0.13
    4:0.17
    5:0.03
    6:0.05
    7:0.19
    8:0.03
    9:0.04
    10:0.08
    11:0.07
    Negative Logits
     mistakenly
    -1.58
    mist
    -1.55
     wrongly
    -1.54
     incorrectly
    -1.53
     falsely
    -1.53
    !=
    -1.52
     differently
    -1.52
    otom
    -1.50
    ationally
    -1.49
    ealous
    -1.49
    POSITIVE LOGITS
     mosqu
    1.68
     firepower
    1.51
     resurg
    1.46
     lineback
    1.42
    amaz
    1.41
     qualitative
    1.38
    ibaba
    1.37
     TBA
    1.36
    gie
    1.36
     Legions
    1.36
    Act Density 0.001%

    No Known Activations