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

    Neuronpedia

    INDEX
    Explanations

    punctuation and formatting symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    deld
    -0.67
     }}>
    -0.67
    oob
    -0.67
    lisi
    -0.66
    midt
    -0.65
    }}}}
    -0.65
     tat
    -0.65
     PropTypes
    -0.65
    Noc
    -0.64
    utiny
    -0.63
    POSITIVE LOGITS
    </strong>
    0.92
     purpoſe
    0.89
     Phry
    0.87
    LLocation
    0.81
    rungsseite
    0.81
     castor
    0.80
    mmä
    0.79
    AddTagHelper
    0.79
     Westmoreland
    0.78
     kasarigan
    0.78
    Act Density 0.047%

    No Known Activations