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

    Neuronpedia

    INDEX
    Explanations

    sentences related to changes in industries or technology

    oai_token-act-pair · gpt-3.5-turbo

    instances of empty sequences or gaps in data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Niet
    -0.63
     Jagu
    -0.60
     Vaugh
    -0.59
     Classics
    -0.58
     antid
    -0.56
    elines
    -0.56
     Moroc
    -0.54
    ichever
    -0.52
     referen
    -0.52
     Ezek
    -0.51
    POSITIVE LOGITS
    ↵Âł
    0.73
    ↵↵
    0.63
    ocaust
    0.62
    \":
    0.61
     ·
    0.58
    îĢ
    0.56
     alot
    0.56
    ui
    0.55
     ]
    0.55
    )?
    0.55
    Act Density 1.850%

    No Known Activations