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

    Neuronpedia

    INDEX
    Explanations

    words related to disasters or impactful events

    oai_token-act-pair · gpt-3.5-turbo

    variations of forms related to the word "daft."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Reviewer
    -0.68
    swick
    -0.67
    ħĭ
    -0.65
     traged
    -0.64
    =-=-=-=-
    -0.64
     axes
    -0.63
    APH
    -0.60
     margins
    -0.60
     Cosponsors
    -0.59
    ãĥŁ
    -0.59
    POSITIVE LOGITS
    geon
    0.80
    zig
    0.76
    atis
    0.73
    ault
    0.73
    lict
    0.73
     Sole
    0.72
    bag
    0.72
    tails
    0.71
    ulf
    0.70
    mort
    0.70
    Act Density 0.093%

    No Known Activations