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

    Neuronpedia

    INDEX
    Explanations

    expressions of gratitude towards the reader

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     JAXBElement
    -0.63
     ſind
    -0.63
    elemField
    -0.62
     localObject
    -0.62
     GenerationType
    -0.61
    expandindo
    -0.61
    ſelf
    -0.59
     unknownFields
    -0.58
     indígen
    -0.58
    endforeach
    -0.57
    POSITIVE LOGITS
     you
    1.18
    <bos>
    0.78
     we
    0.69
    ↵
    0.66
     they
    0.62
     it
    0.58
    .
    0.57
     the
    0.53
     
    0.52
     problems
    0.51
    Act Density 0.454%

    No Known Activations