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

    Neuronpedia

    INDEX
    Explanations

    the word "yeah" as part of the text

    oai_token-act-pair · gpt-3.5-turbo

    affirmative expressions or colloquial agreements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inator
    -0.81
    Fourth
    -0.77
    Daily
    -0.77
    Myth
    -0.73
    士
    -0.71
    Leader
    -0.70
    Medic
    -0.70
    IDS
    -0.69
    Guard
    -0.68
    Hol
    -0.68
    POSITIVE LOGITS
     yeah
    1.18
    yeah
    0.90
    etheless
    0.90
    terday
    0.89
     pardon
    0.85
     sure
    0.85
     Yeah
    0.85
     dunno
    0.83
     yes
    0.83
     alright
    0.79
    Act Density 0.006%

    No Known Activations