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

    Neuronpedia

    INDEX
    Explanations

    the word "Lind" with the highest activation value possible

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Lind."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OPLE
    -0.85
    CLASSIFIED
    -0.78
    Magikarp
    -0.73
    Ø©
    -0.70
    Rated
    -0.67
    Downloadha
    -0.66
    ASED
    -0.66
    avez
    -0.66
    ABLE
    -0.65
    ably
    -0.63
    POSITIVE LOGITS
    gren
    1.16
    strom
    1.09
    enstein
    1.02
    seys
    0.97
    ahl
    0.97
    isf
    0.97
    berg
    0.96
    quist
    0.95
    hart
    0.90
    lasses
    0.89
    Act Density 0.003%

    No Known Activations