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

    Neuronpedia

    INDEX
    Explanations

    contractions with a negative connotation

    oai_token-act-pair · gpt-3.5-turbo

    negative contractions indicating refusal or denial

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    interstitial
    -0.68
    éĥ
    -0.68
    Site
    -0.67
     è£ıè
    -0.64
     ç¥ŀ
    -0.64
    cano
    -0.63
    ancer
    -0.62
    pages
    -0.62
    bard
    -0.61
     Presence
    -0.60
    POSITIVE LOGITS
     necessarily
    1.11
    icably
    1.09
     bother
    1.03
    icable
    1.00
     exactly
    0.86
    urtles
    0.85
    epad
    0.84
    rieve
    0.82
     hesitate
    0.82
     bud
    0.81
    Act Density 0.078%

    No Known Activations