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

    Neuronpedia

    INDEX
    Explanations

    first-person pronouns and references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     he
    -0.66
     himself
    -0.55
     He
    -0.55
     his
    -0.52
    <bos>
    -0.50
    他
    -0.50
    He
    -0.49
     Он
    -0.48
    amling
    -0.48
    他也
    -0.47
    POSITIVE LOGITS
    xtext
    0.70
    featureID
    0.69
     useStyles
    0.67
     ComVisible
    0.66
    endphp
    0.66
    SurfaceView
    0.64
     صوتيه
    0.64
    sizeCache
    0.63
     hObject
    0.62
     AppBundle
    0.61
    Act Density 0.114%

    No Known Activations