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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate personal growth and action-oriented intentions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    amba
    -0.17
    ala
    -0.14
    mun
    -0.14
    δÏĮ
    -0.14
    ahl
    -0.14
    ilib
    -0.13
    ÑĢой
    -0.13
     form
    -0.13
     deductible
    -0.13
     stroke
    -0.13
    POSITIVE LOGITS
    aket
    0.17
     Ryder
    0.15
    ³
    0.15
    ckett
    0.15
    ptron
    0.15
    lemn
    0.15
    oÄŁ
    0.15
    OUSE
    0.14
    åĿª
    0.14
    jun
    0.14
    Act Density 0.146%

    No Known Activations