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

    Neuronpedia

    INDEX
    Explanations

    phrases or sentences containing directives or instructions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ounge
    -0.14
     shown
    -0.14
    iddleware
    -0.14
    ï¸ı
    -0.14
     somehow
    -0.14
    orman
    -0.13
    ities
    -0.13
    anker
    -0.13
    âłĢ
    -0.13
    uss
    -0.13
    POSITIVE LOGITS
    lotte
    0.17
    worthy
    0.17
     yourself
    0.16
    lea
    0.15
    phin
    0.15
    753
    0.15
     plenty
    0.14
    /use
    0.14
    refixer
    0.14
    atham
    0.14
    Act Density 0.093%

    No Known Activations