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

    Neuronpedia

    INDEX
    Explanations

    numeric counts or instances

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "count" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    por
    -0.70
    perty
    -0.69
    etheus
    -0.65
    TPP
    -0.62
     impulse
    -0.61
    agar
    -0.61
     Flavoring
    -0.60
     obser
    -0.59
     Jinn
    -0.59
    wegian
    -0.58
    POSITIVE LOGITS
    enance
    1.89
    downs
    1.04
    esses
    0.84
    ENCY
    0.84
    ess
    0.83
    ries
    0.75
     count
    0.74
    books
    0.73
    rooms
    0.73
    offs
    0.72
    Act Density 0.011%

    No Known Activations