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

    Neuronpedia

    INDEX
    Explanations

    words indicating continuation or ongoing action

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate ongoing processes or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ographical
    -0.75
    ãĥĥãĥĪ
    -0.69
    ortment
    -0.69
    assad
    -0.67
    ethy
    -0.63
    asio
    -0.62
    rection
    -0.61
    ociate
    -0.61
     antidote
    -0.59
    arta
    -0.59
    POSITIVE LOGITS
     unab
    1.32
     uninterrupted
    1.10
     indefinitely
    1.02
     till
    0.96
     unchecked
    0.96
     unchanged
    0.95
     until
    0.94
     onward
    0.93
     ap
    0.92
     throughout
    0.91
    Act Density 0.041%

    No Known Activations