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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the start of a list or point

    oai_token-act-pair · gpt-3.5-turbo

    the word "let's" and its variations or contexts suggesting a call to action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eur
    -0.73
    ELD
    -0.66
     Source
    -0.64
     Citiz
    -0.63
     Allied
    -0.60
    Creat
    -0.60
     Range
    -0.58
     Able
    -0.58
     Slug
    -0.56
     Associated
    -0.55
    POSITIVE LOGITS
     pretend
    0.95
     assume
    0.92
     clarify
    0.88
     gaze
    0.88
     proceed
    0.87
     presume
    0.85
    iblings
    0.84
     suppose
    0.83
     continue
    0.83
     beware
    0.83
    Act Density 0.016%

    No Known Activations