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

    Neuronpedia

    INDEX
    Explanations

    phrases related to events or situations that are developing or happening over time

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to events that are happening or developing over time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Quit
    -0.67
     reservations
    -0.65
     reservation
    -0.65
     Sierra
    -0.65
     quotas
    -0.63
     preference
    -0.63
     penal
    -0.62
     DOS
    -0.61
    Gall
    -0.60
    aint
    -0.60
    POSITIVE LOGITS
     unfold
    3.53
     unfolded
    3.36
     unfolds
    2.92
     unfolding
    2.87
     unravel
    1.73
     transpired
    1.48
     intertw
    1.21
     gripping
    1.14
     engulf
    1.13
     engulfed
    1.10
    Act Density 0.033%

    No Known Activations