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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, especially quotation marks and apostrophes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ProtoMessage
    -0.79
    verwijspagina
    -0.77
     Felic
    -0.72
     schlä
    -0.71
     NSCoder
    -0.64
    TabIndex
    -0.64
    NewUrlParser
    -0.64
    en
    -0.63
    zzleHttp
    -0.63
    InjectAttribute
    -0.63
    POSITIVE LOGITS
    ”
    1.14
    )”
    1.07
    ’”
    1.04
    ]<<"
    1.00
    ]"
    1.00
    %"
    0.99
    ”]
    0.97
    }}"
    0.96
    :”
    0.96
    '"
    0.94
    Act Density 0.275%

    No Known Activations