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

    Neuronpedia

    INDEX
    Explanations

    terms related to herbicides or gardening

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "weed" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ultz
    -0.73
    hematic
    -0.72
    akespe
    -0.71
    ctic
    -0.69
    ropolitan
    -0.68
     inval
    -0.68
    ctica
    -0.67
     rapport
    -0.67
    perty
    -0.66
    rists
    -0.66
    POSITIVE LOGITS
    killer
    0.88
     weed
    0.85
     Seeds
    0.81
    lings
    0.81
    bytes
    0.80
    atio
    0.78
     Weed
    0.77
    hog
    0.76
    ells
    0.76
    edIn
    0.75
    Act Density 0.033%

    No Known Activations