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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate uncertainty or speculation regarding events or facts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.18
    1:0.27
    2:0.03
    3:0.05
    4:0.03
    5:0.11
    6:0.02
    7:0.03
    8:0.06
    9:0.07
    10:0.04
    11:0.04
    Negative Logits
    SPONSORED
    -1.64
    oufl
    -1.56
    Pakistan
    -1.54
    fur
    -1.54
    Fall
    -1.53
    Cover
    -1.50
    iazep
    -1.49
    Hash
    -1.46
    ................................................................
    -1.46
    hide
    -1.44
    POSITIVE LOGITS
     restoring
    1.57
     assigning
    1.50
     isol
    1.49
     Universities
    1.47
     repealing
    1.46
     colleges
    1.43
     obtaining
    1.40
     uncontrolled
    1.40
     educating
    1.38
     separating
    1.37
    Act Density 0.119%

    No Known Activations