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

    Neuronpedia

    INDEX
    Explanations

    words indicating significant quantities or emphatic descriptors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ists
    -0.19
    iac
    -0.17
    ROS
    -0.15
    ros
    -0.15
    uds
    -0.15
    _velocity
    -0.14
    hower
    -0.14
    eka
    -0.14
     visit
    -0.14
    ials
    -0.14
    POSITIVE LOGITS
    lying
    0.17
    ylon
    0.17
    ACKET
    0.16
    edl
    0.15
    ë§IJ
    0.15
    Ỽ
    0.15
    oi
    0.14
     æ¬
    0.14
    amac
    0.13
    ooled
    0.13
    Act Density 0.003%

    No Known Activations