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

    Neuronpedia

    INDEX
    Explanations

    phrases containing scientific terminology or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.08
    1:0.08
    2:0.08
    3:0.07
    4:0.07
    5:0.09
    6:0.07
    7:0.06
    8:0.09
    9:0.10
    10:0.08
    11:0.09
    Negative Logits
    undo
    -1.67
    hani
    -1.64
    vati
    -1.61
    veyard
    -1.58
    ulia
    -1.56
    orea
    -1.55
    ividual
    -1.52
    react
    -1.45
    bern
    -1.44
    razil
    -1.44
    POSITIVE LOGITS
    aunders
    1.49
     merc
    1.48
     Mercenary
    1.46
     Bungie
    1.45
     Battalion
    1.45
     Saiyan
    1.43
     Removal
    1.43
     licens
    1.43
     SOFTWARE
    1.41
     Cerberus
    1.41
    Act Density 0.000%

    No Known Activations