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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate actions or decisions being made

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ("")]
    -0.63
     Tole
    -0.56
     Reſ
    -0.55
     Gher
    -0.54
    ])[
    -0.54
     []),
    -0.52
     Apre
    -0.52
     []);
    -0.50
     Olen
    -0.50
     Epif
    -0.50
    POSITIVE LOGITS
     jScrollPane
    0.67
     happened
    0.60
     hacerlo
    0.60
     happen
    0.59
    يكب
    0.59
     farlo
    0.59
    Diweddarwch
    0.58
    hljs
    0.58
    pagnole
    0.57
     happens
    0.56
    Act Density 0.422%

    No Known Activations