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

    Neuronpedia

    INDEX
    Explanations

    contractions where the words "do" and "not" are joined together

    oai_token-act-pair · gpt-3.5-turbo

    negations or phrases conveying refusal or resistance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ancer
    -0.73
    Site
    -0.69
    cano
    -0.68
    Laun
    -0.63
    pages
    -0.62
     è£ıè
    -0.62
    itiz
    -0.62
    Pure
    -0.61
     Britann
    -0.60
    Intern
    -0.60
    POSITIVE LOGITS
     necessarily
    1.01
     bother
    0.97
    icably
    0.96
    urtles
    0.88
    icable
    0.85
    rieve
    0.85
     hesitate
    0.82
     exactly
    0.81
     seem
    0.77
     surpr
    0.75
    Act Density 0.078%

    No Known Activations