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

    Neuronpedia

    INDEX
    Explanations

    strings of consecutive quotation marks or apostrophes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     giao
    -0.74
    ories
    -0.72
    ory
    -0.71
     Montal
    -0.70
    ly
    -0.69
     IEnumerable
    -0.69
     disper
    -0.69
    pel
    -0.68
    [::-
    -0.68
     Nis
    -0.68
    POSITIVE LOGITS
    }}"
    1.25
    %"
    1.14
     }}"
    1.10
    ]"
    1.09
    ')}}"
    1.08
    }"
    1.07
    )"
    1.06
    ')"
    1.05
    ?"
    1.03
    ']")
    1.02
    Act Density 0.100%

    No Known Activations