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

    Neuronpedia

    INDEX
    Explanations

    sentence fragments ending with a specific word

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "can" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pires
    -0.76
    arthed
    -0.75
     favors
    -0.70
    rang
    -0.65
     Mant
    -0.64
    bush
    -0.64
     Appears
    -0.64
     Moz
    -0.62
    existent
    -0.60
     scrapped
    -0.59
    POSITIVE LOGITS
    't
    1.48
    NOT
    1.06
     find
    1.04
    berra
    1.03
     learn
    1.01
     browse
    0.96
     choose
    0.96
     imagine
    0.95
     customize
    0.95
     see
    0.94
    Act Density 0.082%

    No Known Activations