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

    Neuronpedia

    INDEX
    Explanations

    phrases related to concealment or suppression of information or issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.02
    2:0.06
    3:0.05
    4:0.16
    5:0.03
    6:0.08
    7:0.33
    8:0.04
    9:0.03
    10:0.06
    11:0.06
    Negative Logits
    pent
    -1.70
    Dim
    -1.55
     wait
    -1.55
    iator
    -1.46
    suff
    -1.42
    adjust
    -1.41
    stood
    -1.38
    QB
    -1.36
     delinqu
    -1.36
     spacing
    -1.35
    POSITIVE LOGITS
    estones
    1.63
    estone
    1.47
    avorite
    1.43
     rubble
    1.40
     Oaks
    1.40
     prizes
    1.38
     blows
    1.37
     ballots
    1.35
    Winner
    1.35
     graves
    1.32
    Act Density 0.005%

    No Known Activations