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

    Neuronpedia

    INDEX
    Explanations

    terms related to fields or domains of expertise and activity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .imp
    -0.14
     KN
    -0.14
    deniz
    -0.14
    AIT
    -0.13
     ç¦
    -0.13
    dish
    -0.13
    doc
    -0.13
    mploy
    -0.13
    ofile
    -0.13
    urous
    -0.13
    POSITIVE LOGITS
    кÑĥлÑı
    0.17
    rawer
    0.17
    anja
    0.17
    jeta
    0.16
    esk
    0.16
    icit
    0.15
    anter
    0.14
    anco
    0.14
    anj
    0.14
    umbed
    0.14
    Act Density 0.008%

    No Known Activations