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

    Neuronpedia

    INDEX
    Explanations

    words related to hawks and hawk-related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to "hawks" in a political or military context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ALLY
    -0.77
     Mysteries
    -0.75
     Scotia
    -0.75
     Pixie
    -0.73
     Winchester
    -0.71
     Cth
    -0.70
     Annotations
    -0.69
     Investigator
    -0.69
     Dragonbound
    -0.68
    DEP
    -0.67
    POSITIVE LOGITS
    keye
    1.27
     haw
    1.23
    kish
    1.21
     hawk
    1.03
    aii
    0.98
    keyes
    0.93
    acles
    0.91
    ittle
    0.90
    nuts
    0.88
    nut
    0.88
    Act Density 0.020%

    No Known Activations