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

    Neuronpedia

    INDEX
    Explanations

    words related to something being heavily emphasized or focused on

    oai_token-act-pair · gpt-3.5-turbo

    the repeated use of the word "heavily" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tein
    -0.89
     Thumbnails
    -0.80
     Chaser
    -0.78
    iry
    -0.78
     Smile
    -0.70
     Machina
    -0.69
     Fidel
    -0.68
    atu
    -0.66
     greatness
    -0.66
    psons
    -0.66
    POSITIVE LOGITS
     subsid
    0.91
     concentrated
    0.90
     subsidized
    0.85
     armoured
    0.85
     armored
    0.84
     reliant
    0.83
     discounted
    0.81
     recruited
    0.81
     relied
    0.80
     populated
    0.80
    Act Density 0.012%

    No Known Activations