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

    Neuronpedia

    INDEX
    Explanations

    phrases related to high interest or eagerness

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    channelAvailability
    -1.00
    utical
    -0.69
    天
    -0.67
    UID
    -0.67
    idences
    -0.66
    mbuds
    -0.65
    agi
    -0.65
    ania
    -0.64
    ICAN
    -0.63
    inventoryQuantity
    -0.63
    POSITIVE LOGITS
    ly
    1.25
    eful
    0.97
    irection
    0.96
    emouth
    0.95
    ness
    0.90
    est
    0.83
     eyed
    0.82
    stone
    0.80
    fully
    0.80
     keen
    0.77
    Act Density 0.011%

    No Known Activations