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

    Neuronpedia

    INDEX
    Explanations

    references to clauses and conditions in a narrative or argument

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     however
    -0.82
     entanto
    -0.80
    however
    -0.73
     übrigens
    -0.72
    甚至
    -0.65
     regretted
    -0.63
     jopa
    -0.62
     cependant
    -0.62
     deshalb
    -0.62
     daher
    -0.60
    POSITIVE LOGITS
    畢竟
    0.85
    毕竟
    0.83
     already
    0.82
    Хьажоргаш
    0.81
     przecież
    0.78
     Schließlich
    0.73
     vốn
    0.72
    already
    0.71
    又不是
    0.70
    そもそも
    0.68
    Act Density 0.723%

    No Known Activations