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

    Neuronpedia

    INDEX
    Explanations

    references to addiction and its related issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     entanto
    -0.77
     however
    -0.76
    甚至
    -0.68
     jopa
    -0.66
     sogar
    -0.64
    however
    -0.64
     dokonce
    -0.63
     bahkan
    -0.60
     thậm
    -0.60
     hatta
    -0.58
    POSITIVE LOGITS
     przecież
    1.01
     ohnehin
    0.99
     already
    0.94
    畢竟
    0.92
     inherently
    0.91
    Хьажоргаш
    0.88
    毕竟
    0.87
    already
    0.87
     이미
    0.81
     Schließlich
    0.80
    Act Density 0.740%

    No Known Activations