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

    Neuronpedia

    INDEX
    Explanations

    keywords related to comparisons involving time

    oai_token-act-pair · gpt-3.5-turbo

    references to consistency and repetition in various situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    *=-
    -0.65
    live
    -0.62
    arest
    -0.61
     Recomm
    -0.59
     Bei
    -0.58
    aire
    -0.58
    EXP
    -0.58
     Hawai
    -0.58
    atown
    -0.58
    AFTA
    -0.58
    POSITIVE LOGITS
     vein
    0.93
     thing
    0.87
     exact
    0.81
     amount
    0.73
    rity
    0.72
     playbook
    0.72
     reason
    0.69
     ol
    0.68
     kind
    0.68
    worldly
    0.67
    Act Density 0.045%

    No Known Activations