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

    Neuronpedia

    INDEX
    Explanations

    specific names and terms related to events and discussions, possibly in a social media context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    parsedMessage
    -1.54
     miniaturka
    -1.47
     queſta
    -1.46
     témoig
    -1.38
    majánló
    -1.37
    expandindo
    -1.34
     desmotivaciones
    -1.32
     indígen
    -1.30
    <unused43>
    -1.30
    <pad>
    -1.30
    POSITIVE LOGITS
    ,
    0.47
    .
    0.47
    ↵
    0.43
    !
    0.43
     
    0.43
    :
    0.42
    <eos>
    0.41
    ↵↵
    0.40
    )
    0.38
     |
    0.37
    Act Density 0.625%

    No Known Activations