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

    Neuronpedia

    INDEX
    Explanations

    references to the reader or audience in a conversational context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orthy
    -0.15
    .nz
    -0.15
    REFERRED
    -0.15
    own
    -0.15
    owi
    -0.14
    atings
    -0.14
     Analyzer
    -0.14
    bach
    -0.13
    daughter
    -0.13
    OWN
    -0.13
    POSITIVE LOGITS
     guys
    0.69
     Guys
    0.52
     guy
    0.42
     Guy
    0.37
    Guy
    0.36
     folks
    0.36
     gentlemen
    0.30
     boys
    0.27
    fol
    0.26
    ’all
    0.26
    Act Density 0.126%

    No Known Activations