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

    Neuronpedia

    INDEX
    Explanations

    assertive language indicating certainty or confirmation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    How
    -0.67
     How
    -0.63
     tradition
    -0.60
     Baer
    -0.59
     Mier
    -0.59
    rion
    -0.57
     Bau
    -0.56
    いかに
    -0.55
    ốc
    -0.54
    jum
    -0.54
    POSITIVE LOGITS
     definitely
    1.48
     Definitely
    1.40
     definately
    1.40
    Definitely
    1.35
    definitely
    1.28
     definite
    1.21
     certainly
    1.11
    definite
    1.09
     Certainly
    1.08
     certainement
    0.99
    Act Density 0.060%

    No Known Activations