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

    Neuronpedia

    INDEX
    Explanations

    spoken or finished quotation marks in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Montal
    -0.85
    inq
    -0.81
    eſt
    -0.81
     ioutil
    -0.78
    vastava
    -0.78
     Mait
    -0.75
     Gier
    -0.73
    CCIÓN
    -0.73
     Grot
    -0.73
     Lic
    -0.72
    POSITIVE LOGITS
    ?"
    1.26
    ]"
    1.19
    }}"
    1.18
    )"
    1.18
    }"
    1.18
    ="#"
    1.11
    !"
    1.11
    '"
    1.09
    >"
    1.08
    ")
    1.07
    Act Density 0.310%

    No Known Activations