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

    Neuronpedia

    INDEX
    Explanations

    phrases starting with "Don't"

    oai_token-act-pair · gpt-3.5-turbo

    phrases that use the contraction "don't."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Reviewer
    -0.79
    amer
    -0.77
    Site
    -0.65
    bard
    -0.65
    itiz
    -0.65
    interstitial
    -0.64
    éĥ
    -0.64
     Britann
    -0.64
     è£ıè
    -0.64
    cano
    -0.63
    POSITIVE LOGITS
     necessarily
    1.23
     bother
    1.05
     exactly
    1.01
    icably
    0.96
    icable
    0.92
     gonna
    0.90
     really
    0.88
     quite
    0.88
    urtles
    0.84
     even
    0.82
    Act Density 0.103%

    No Known Activations