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

    Neuronpedia

    INDEX
    Explanations

    high activation values associated with options or values in select elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    stateParams
    -0.50
    }));
    -0.48
    '])){
    -0.48
    Doppel
    -0.47
    ("/{
    -0.46
    jonen
    -0.46
    案
    -0.46
    랜
    -0.45
    ]));
    -0.44
    iecie
    -0.44
    POSITIVE LOGITS
    Value
    2.62
     Value
    2.47
     value
    2.40
    value
    2.29
     VALUE
    2.17
    VALUE
    2.16
     valeur
    1.69
     Values
    1.66
     values
    1.63
     VALUES
    1.60
    Act Density 0.066%

    No Known Activations