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

    Neuronpedia

    INDEX
    Explanations

    references to identified groups of individuals or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.01
    1:0.02
    2:0.21
    3:0.18
    4:0.15
    5:0.03
    6:0.04
    7:0.09
    8:0.04
    9:0.03
    10:0.07
    11:0.07
    Negative Logits
    ć
    -1.45
     BAS
    -1.44
    ô
    -1.44
     nm
    -1.43
    oons
    -1.43
     guiActiveUn
    -1.42
    bah
    -1.42
    idity
    -1.36
    ouch
    -1.32
     srf
    -1.28
    POSITIVE LOGITS
    eligible
    1.68
     barred
    1.49
     TAMADRA
    1.47
     deadliest
    1.39
     delinquent
    1.38
     awaiting
    1.37
    liest
    1.34
     embattled
    1.33
     quir
    1.33
    apest
    1.32
    Act Density 0.034%

    No Known Activations