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

    Neuronpedia

    INDEX
    Explanations

    phrases containing the word "fed"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "fed" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abilities
    -0.80
    ability
    -0.80
     Romance
    -0.76
    undle
    -0.70
     Odyssey
    -0.67
    ura
    -0.66
    acular
    -0.64
    eness
    -0.64
     Holland
    -0.64
    Theme
    -0.63
    POSITIVE LOGITS
     fed
    3.83
    fed
    2.39
     feeding
    1.77
     feeds
    1.77
     feed
    1.73
    Fed
    1.70
     Feed
    1.48
    feeding
    1.41
    feed
    1.41
     starved
    1.24
    Act Density 0.015%

    No Known Activations