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

    Neuronpedia

    INDEX
    Explanations

    concepts related to personal interests and motivations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    \grid
    -0.20
    izr
    -0.18
    ekim
    -0.16
    undreds
    -0.16
    aload
    -0.16
    voje
    -0.15
    ÏģÏħ
    -0.15
     dilig
    -0.14
    anca
    -0.14
    nets
    -0.14
    POSITIVE LOGITS
    ache
    0.15
    кÑĥп
    0.15
    able
    0.15
    itan
    0.15
    mnt
    0.14
    erton
    0.14
    iani
    0.14
    íĤ¹
    0.14
     vidé
    0.14
    SR
    0.14
    Act Density 0.232%

    No Known Activations