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

    Neuronpedia

    INDEX
    Explanations

    references to vegetation, particularly bushes and forests

    oai_token-act-pair · gpt-3.5-turbo

    references to bush-related topics and terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    icates
    -0.70
    ications
    -0.69
    ICO
    -0.68
    xit
    -0.67
    uez
    -0.67
     Luthor
    -0.64
     Mellon
    -0.64
    ysis
    -0.64
    odore
    -0.64
     insidious
    -0.64
    POSITIVE LOGITS
    fires
    1.09
     bush
    0.94
    tree
    0.94
    fire
    0.93
    wh
    0.91
    keeping
    0.91
    keeper
    0.91
    meat
    0.90
    bare
    0.90
    craft
    0.88
    Act Density 0.015%

    No Known Activations