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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate purposes or target audiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wise
    -0.17
    tee
    -0.15
    yn
    -0.14
    chez
    -0.14
     Roose
    -0.14
    outh
    -0.14
    ateur
    -0.14
    .utf
    -0.14
    porte
    -0.13
    eb
    -0.13
    POSITIVE LOGITS
     sale
    0.18
    (PHP
    0.17
    -sale
    0.15
     Sale
    0.15
    INGLE
    0.15
    ró
    0.14
    ges
    0.14
    LARI
    0.14
     hire
    0.14
    odge
    0.14
    Act Density 0.120%

    No Known Activations