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

    Neuronpedia

    INDEX
    Explanations

    references to a specific publication or news source

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.13
    1:0.04
    2:0.04
    3:0.06
    4:0.27
    5:0.10
    6:0.04
    7:0.04
    8:0.06
    9:0.09
    10:0.04
    11:0.03
    Negative Logits
    ?,
    -2.46
    ibal
    -2.07
    igible
    -2.03
     Detected
    -1.93
    ensis
    -1.92
    '?
    -1.91
    ?:
    -1.91
    ?",
    -1.89
    ;;;;;;;;;;;;
    -1.84
    .?
    -1.84
    POSITIVE LOGITS
    rollers
    2.00
    Wa
    1.91
    Untitled
    1.86
     Moonlight
    1.84
    Ble
    1.80
    itu
    1.75
     Jem
    1.75
     disapp
    1.74
    ッド
    1.73
    ewater
    1.73
    Act Density 0.000%

    No Known Activations