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

    Neuronpedia

    INDEX
    Explanations

    references to specific dates and broadcasts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.02
    2:0.14
    3:0.14
    4:0.15
    5:0.04
    6:0.04
    7:0.13
    8:0.04
    9:0.05
    10:0.09
    11:0.10
    Negative Logits
    dress
    -1.81
    olars
    -1.69
    mine
    -1.40
    itance
    -1.37
    foundation
    -1.37
     WATCHED
    -1.36
    alks
    -1.35
    cale
    -1.32
    ise
    -1.32
    rimination
    -1.32
    POSITIVE LOGITS
     tru
    1.70
     exclusively
    1.43
    Interstitial
    1.41
    Boo
    1.40
     mins
    1.36
     appre
    1.35
    EngineDebug
    1.35
    COMPLE
    1.34
    Tonight
    1.31
     nightly
    1.30
    Act Density 0.001%

    No Known Activations