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

    Neuronpedia

    INDEX
    Explanations

    terms indicating existence or presence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.08
    1:0.07
    2:0.08
    3:0.09
    4:0.08
    5:0.08
    6:0.06
    7:0.08
    8:0.07
    9:0.09
    10:0.08
    11:0.09
    Negative Logits
    idth
    -2.87
    verend
    -2.80
    Bride
    -2.79
    assic
    -2.70
    umbers
    -2.70
    ngth
    -2.63
     entreprene
    -2.63
    urchase
    -2.55
    skilled
    -2.53
    wyn
    -2.53
    POSITIVE LOGITS
     Nero
    3.68
     Gaia
    3.06
     Dome
    3.05
     DN
    2.99
     MSM
    2.93
     Cosmos
    2.91
     Chimera
    2.90
     SAP
    2.78
     HF
    2.75
     Null
    2.75
    Act Density 0.000%

    No Known Activations