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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the lack of response or acknowledgment to a certain situation

    oai_token-act-pair · gpt-3.5-turbo

    negations or expressions of non-responsiveness in communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    interstitial
    -0.79
    entric
    -0.73
    stakes
    -0.73
    FAQ
    -0.70
    ership
    -0.70
    Reader
    -0.70
    wrapper
    -0.70
    Maker
    -0.67
    former
    -0.66
    =-=-=-=-=-=-=-=-
    -0.65
    POSITIVE LOGITS
     necessarily
    1.04
     hesitate
    0.98
    icably
    0.91
     adequately
    0.90
     initially
    0.88
     originally
    0.88
     exactly
    0.87
     foresee
    0.86
     disappoint
    0.86
     bother
    0.81
    Act Density 0.151%

    No Known Activations