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

    Neuronpedia

    INDEX
    Explanations

    phrases related to event logistics and instructions

    oai_token-act-pair · gpt-3.5-turbo

    references to events and coordination of instructions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    terday
    -0.75
    ĸļ
    -0.73
     slam
    -0.70
     cuts
    -0.69
     himself
    -0.68
    utics
    -0.67
     outweigh
    -0.66
    uca
    -0.65
     vir
    -0.65
     herself
    -0.65
    POSITIVE LOGITS
    Example
    1.19
    Disclaimer
    1.14
    NOTE
    1.10
    Additional
    1.09
    Important
    1.08
    Examples
    1.08
    Recommended
    1.06
    Please
    1.06
    Currently
    1.02
    Methods
    0.99
    Act Density 0.580%

    No Known Activations