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

    Neuronpedia

    INDEX
    Explanations

    expressions of confusion and requests for help

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    MLE
    -0.16
     quarantine
    -0.14
    osg
    -0.14
    ınca
    -0.14
     Fitzgerald
    -0.13
    æ¶Īè´¹
    -0.13
    maz
    -0.13
    ëıĮ
    -0.13
    urre
    -0.13
    URRE
    -0.13
    POSITIVE LOGITS
    Ķ
    0.15
    grily
    0.14
    department
    0.14
     /\
    0.14
    uffs
    0.13
    esin
    0.13
     patter
    0.13
     вÑĢемен
    0.13
    /Admin
    0.13
    IFO
    0.13
    Act Density 0.043%

    No Known Activations