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

    Neuronpedia

    INDEX
    Explanations

    the name "Pradhan"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Han"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     CONTROL
    -0.63
     Mov
    -0.62
     keys
    -0.62
     Nato
    -0.61
     key
    -0.61
     responsive
    -0.58
     NATO
    -0.57
     ESC
    -0.56
     nonexistent
    -0.56
     US
    -0.56
    POSITIVE LOGITS
    han
    4.54
    hani
    1.95
    hal
    1.57
    hy
    1.56
    ha
    1.52
    har
    1.50
    hin
    1.45
    hu
    1.40
    hs
    1.38
    hang
    1.37
    Act Density 0.005%

    No Known Activations