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

    Neuronpedia

    INDEX
    Explanations

    phrases related to military activities

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "the."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    MODE
    -0.73
     followed
    -0.71
    tions
    -0.67
    ãģı
    -0.66
     compared
    -0.64
    Attempts
    -0.63
    icip
    -0.63
    manship
    -0.62
     accordingly
    -0.61
    ItemImage
    -0.60
    POSITIVE LOGITS
     outset
    1.55
     standpoint
    1.45
     perspective
    1.20
     sidelines
    1.16
     vantage
    1.13
     depths
    1.10
     mouths
    0.95
     brink
    0.95
     viewpoint
    0.94
     balcony
    0.94
    Act Density 0.156%

    No Known Activations