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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "like."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -1.86
    /***
    -0.58
    Enlaces
    -0.57
    ///**
    -0.56
    ref
    -0.56
    ыгана
    -0.54
    乜
    -0.54
    Παραπομπές
    -0.54
    Eksterne
    -0.53
    </table>
    -0.52
    POSITIVE LOGITS
     impractica
    1.41
     impra
    1.15
     disagre
    1.10
     perfon
    1.08
     liberality
    1.07
     unwarran
    1.03
     sovere
    1.03
     viciss
    1.02
     reluct
    1.01
     ftu
    1.01
    Act Density 0.084%

    No Known Activations