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

    Neuronpedia

    INDEX
    Explanations

    the beginning of sections or paragraphs in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ])+
    -0.37
     },
    -0.35
     
    -0.34
    }
    -0.34
    s
    -0.34
    }}+
    -0.34
    ])*
    -0.34
    ）
    -0.33
    1
    -0.33
     }
    -0.33
    POSITIVE LOGITS
    <bos>
    0.78
     Geſch
    0.70
     Weiſe
    0.68
    <unused32>
    0.68
     détect
    0.67
    <unused41>
    0.67
    <unused79>
    0.67
    <unused14>
    0.67
    <unused8>
    0.67
    [@BOS@]
    0.67
    Act Density 0.330%

    No Known Activations