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

    Neuronpedia

    INDEX
    Explanations

    greetings or introductions

    oai_token-act-pair · gpt-3.5-turbo

    instances of greeting or casual salutations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Awakens
    -0.81
    */(
    -0.78
    )</
    -0.75
     Rebell
    -0.74
     rall
    -0.70
    士
    -0.69
     Twain
    -0.65
     Cove
    -0.62
    parts
    -0.61
    managed
    -0.60
    POSITIVE LOGITS
    yip
    0.85
    earch
    0.84
    Fi
    0.84
    Hi
    0.78
    ya
    0.75
    hey
    0.75
    Bs
    0.74
    ibel
    0.73
    scribe
    0.73
    roy
    0.73
    Act Density 0.009%

    No Known Activations