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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating capability or potential in relation to actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    تب
    -0.14
    indo
    -0.14
    اÙħبر
    -0.14
    j
    -0.14
    jur
    -0.13
    stadt
    -0.13
    Ø°
    -0.13
     practise
    -0.13
    vil
    -0.13
    pora
    -0.13
    POSITIVE LOGITS
    cia
    0.15
    omin
    0.15
    адки
    0.15
    (Intent
    0.14
    ida
    0.14
    ɵ
    0.14
    unan
    0.14
    ëĶĶìĭľ
    0.14
    -bodied
    0.14
    flater
    0.14
    Act Density 0.022%

    No Known Activations