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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating skepticism or doubt

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    also
    -0.58
     snart
    -0.58
    hopefully
    -0.57
     also
    -0.57
    SOME
    -0.57
    ALREADY
    -0.57
     también
    -0.56
     tambi
    -0.56
     hopefully
    -0.55
    already
    -0.55
    POSITIVE LOGITS
     ever
    1.72
     EVER
    1.33
     siquiera
    1.22
     even
    1.18
     Ever
    1.13
     jemals
    1.11
    Ever
    1.08
    ever
    1.08
     bothered
    1.06
     bothering
    1.04
    Act Density 0.702%

    No Known Activations