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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating changes in levels or dynamics over time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     
    -0.46
    ↵↵
    -0.45
     da
    -0.45
     c
    -0.44
     most
    -0.44
     du
    -0.44
     le
    -0.44
     des
    -0.43
    <eos>
    -0.42
     Des
    -0.42
    POSITIVE LOGITS
    GEBURTSDATUM
    1.02
     typelib
    1.00
     Efq
    0.95
     Majefty
    0.94
    SequentialGroup
    0.93
     ―――――
    0.88
    AndEndTag
    0.88
    UnknownFieldSet
    0.87
    Zeneca
    0.86
     auffi
    0.86
    Act Density 0.786%

    No Known Activations