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

    Neuronpedia

    INDEX
    Explanations

    variations and mentions of the word "sort."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hip
    -0.20
    ummer
    -0.19
    uria
    -0.16
    ous
    -0.16
    ÑĮÑĤе
    -0.15
    allet
    -0.15
    ording
    -0.15
    imals
    -0.15
    itation
    -0.14
    ized
    -0.14
    POSITIVE LOGITS
    iment
    0.19
    .Sort
    0.17
    ileges
    0.17
    alim
    0.16
    ilege
    0.16
    ầm
    0.15
    red
    0.15
    ative
    0.15
     sobie
    0.15
    containers
    0.14
    Act Density 0.013%

    No Known Activations