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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating intentions or future actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    utin
    -0.16
    иÑģлов
    -0.15
    ĥ
    -0.15
    .nih
    -0.14
     Wie
    -0.14
    utow
    -0.14
    à¹ģà¸ķ
    -0.13
    elts
    -0.13
    uent
    -0.13
     COPYING
    -0.13
    POSITIVE LOGITS
    azor
    0.15
     Hoch
    0.14
    816
    0.14
    ocha
    0.14
     Darren
    0.14
     possession
    0.14
    Reuse
    0.13
    ëł¹
    0.13
     Horton
    0.13
    och
    0.13
    Act Density 0.410%

    No Known Activations