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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific bird names

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of birds

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     func
    -0.67
     um
    -0.65
     AFP
    -0.62
     molten
    -0.61
     Mori
    -0.61
     grinding
    -0.60
     Bundes
    -0.59
     indis
    -0.59
     housing
    -0.59
     explosive
    -0.59
    POSITIVE LOGITS
    bird
    4.54
    birds
    3.75
    Bird
    2.32
     Bird
    1.80
     Birds
    1.55
    hawk
    1.46
     bird
    1.39
    hawks
    1.35
    bug
    1.35
    fly
    1.35
    Act Density 0.019%

    No Known Activations