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

    Neuronpedia

    INDEX
    Explanations

    references to a specific individual, likely in a historical or narrative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.09
    1:0.09
    2:0.08
    3:0.07
    4:0.09
    5:0.07
    6:0.08
    7:0.07
    8:0.08
    9:0.08
    10:0.07
    11:0.08
    Negative Logits
    idis
    -2.08
    Streamer
    -2.07
    apter
    -2.07
    hari
    -2.07
    add
    -1.97
    resa
    -1.96
    poke
    -1.94
    atalie
    -1.89
    iliate
    -1.87
     Danielle
    -1.86
    POSITIVE LOGITS
    olation
    2.02
     bombed
    2.02
     populated
    2.00
    )).
    1.92
    olated
    1.91
     Hits
    1.87
     hits
    1.85
     Built
    1.83
     brut
    1.82
     Secondly
    1.78
    Act Density 0.000%

    No Known Activations