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

    Neuronpedia

    INDEX
    Explanations

    concepts related to protection and status classification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ajo
    -0.15
    ongan
    -0.14
    bounding
    -0.14
    -Speed
    -0.14
     Vul
    -0.14
    stro
    -0.13
     Styles
    -0.13
    anean
    -0.13
    lrt
    -0.13
     ske
    -0.12
    POSITIVE LOGITS
     status
    1.15
    status
    0.99
     Status
    0.99
    -status
    0.90
    Status
    0.88
    .status
    0.85
    _status
    0.84
     STATUS
    0.82
     statuses
    0.80
     ÑģÑĤаÑĤÑĥÑģ
    0.77
    Act Density 0.104%

    No Known Activations