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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating an overall assessment or summary of situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iel
    -0.16
    burg
    -0.15
    isco
    -0.15
    ovsky
    -0.15
    sport
    -0.15
    rol
    -0.14
    oret
    -0.14
    ượt
    -0.14
     Dj
    -0.14
    nt
    -0.14
    POSITIVE LOGITS
    igator
    0.19
    mente
    0.17
    -purpose
    0.17
    ìłģìľ¼ë¡ľ
    0.16
     sense
    0.16
    ihn
    0.16
    /general
    0.16
    anton
    0.16
    lsru
    0.16
    ìłģìĿ¸
    0.15
    Act Density 0.016%

    No Known Activations