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

    Neuronpedia

    INDEX
    Explanations

    the name "Linda."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ̣
    -0.21
    Unload
    -0.15
    unga
    -0.15
     Pul
    -0.15
    stal
    -0.14
    ran
    -0.14
     Tod
    -0.14
    βά
    -0.14
    _HELPER
    -0.14
     Charge
    -0.14
    POSITIVE LOGITS
    bjerg
    0.16
    794
    0.16
    972
    0.15
    uzzer
    0.15
    379
    0.15
    heit
    0.15
    SPATH
    0.15
    æŁĦ
    0.14
    571
    0.14
    agini
    0.14
    Act Density 0.005%

    No Known Activations