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

    Neuronpedia

    INDEX
    Explanations

    mentions of marine animals specifically killer whales

    oai_token-act-pair · gpt-3.5-turbo

    references to killer whales

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ational
    -0.91
    ional
    -0.91
    ourced
    -0.88
    ADRA
    -0.87
    edu
    -0.86
    ibly
    -0.84
    ured
    -0.83
    isse
    -0.83
    uration
    -0.82
    bles
    -0.78
    POSITIVE LOGITS
    killer
    1.00
     whales
    0.99
     whale
    0.87
     killer
    0.85
     spree
    0.84
     instinct
    0.84
    knife
    0.82
     blow
    0.76
     killers
    0.73
    fish
    0.72
    Act Density 0.036%

    No Known Activations