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

    Neuronpedia

    INDEX
    Explanations

    words related to significant emphasis or importance

    oai_token-act-pair · gpt-3.5-turbo

    the word "heavily" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atu
    -0.76
    tein
    -0.76
    iry
    -0.76
    psons
    -0.71
    iott
    -0.70
    arium
    -0.70
     Commissioners
    -0.69
    thood
    -0.67
    abad
    -0.67
    ensis
    -0.67
    POSITIVE LOGITS
     reliant
    0.90
     subsid
    0.84
     discounted
    0.83
     redacted
    0.83
     concentrated
    0.82
     populated
    0.81
     indebted
    0.81
     invested
    0.81
     recruited
    0.80
     relied
    0.79
    Act Density 0.037%

    No Known Activations