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

    Neuronpedia

    INDEX
    Explanations

    terms related to technology, magical abilities, and their consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     freilich
    -1.24
     offenbar
    -1.08
     ostensibly
    -0.89
     doubtless
    -0.88
     ―――――
    -0.86
    Herzliche
    -0.86
     imidlertid
    -0.84
     guère
    -0.83
     jedenfalls
    -0.83
     manifestly
    -0.82
    POSITIVE LOGITS
     alot
    0.98
    慢慢的
    0.96
     betek
    0.96
     didalam
    0.95
    非常的
    0.94
     disini
    0.91
     dimana
    0.91
     diatas
    0.89
     данного
    0.89
     aswell
    0.89
    Act Density 3.027%

    No Known Activations