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

    Neuronpedia

    INDEX
    Explanations

    last names of people

    oai_token-act-pair · gpt-3.5-turbo

    proper names, specifically individuals mentioned in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ..."
    -0.79
    bound
    -0.63
     [|
    -0.61
    .ãĢį
    -0.61
    .","
    -0.61
    Bound
    -0.61
     ().
    -0.61
    }.
    -0.60
    ;}
    -0.59
    taboola
    -0.59
    POSITIVE LOGITS
    espie
    0.88
     meanwhile
    0.78
    ource
    0.75
    enegger
    0.74
     acknowledges
    0.72
    anyahu
    0.72
    ashtra
    0.71
    utsche
    0.70
    imore
    0.68
    resy
    0.68
    Act Density 0.281%

    No Known Activations