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

    Neuronpedia

    INDEX
    Explanations

    phrases stating an opinion or acknowledging a contrasting perspective

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "that said."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    prus
    -0.80
    Street
    -0.76
     Flavoring
    -0.73
    elled
    -0.70
    Tai
    -0.67
    çĶ°
    -0.66
    MEN
    -0.65
     Cars
    -0.64
     Editors
    -0.63
    cat
    -0.63
    POSITIVE LOGITS
     caveats
    0.69
     respectfully
    0.68
    nostic
    0.67
    itivity
    0.66
     caveat
    0.66
     doubts
    0.66
     reciproc
    0.65
     goodbye
    0.65
     aside
    0.64
    ratulations
    0.64
    Act Density 0.035%

    No Known Activations