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

    Neuronpedia

    INDEX
    Explanations

    actions related to prison breaks and escapes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    _TLS
    -0.17
    mods
    -0.16
    landing
    -0.16
    zos
    -0.15
     "-//
    -0.15
    ابت
    -0.15
    .inflate
    -0.14
     далÑĸ
    -0.14
     ä¿¡
    -0.14
    گاÙĨÛĮ
    -0.14
    POSITIVE LOGITS
    _thumb
    0.15
     from
    0.14
     n
    0.14
     Collider
    0.14
    aps
    0.14
    ectar
    0.14
     Coll
    0.14
     setters
    0.14
     Homer
    0.14
     set
    0.14
    Act Density 0.067%

    No Known Activations