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

    Neuronpedia

    INDEX
    Explanations

    character names and their relationships in a narrative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ="__
    -0.16
    rab
    -0.15
    _CM
    -0.15
    eger
    -0.14
    inspection
    -0.14
    elligent
    -0.14
    aginator
    -0.14
    ãĥĥãĥĦ
    -0.14
    заб
    -0.14
    ÄŁan
    -0.13
    POSITIVE LOGITS
     soap
    0.30
     Soap
    0.27
     Coron
    0.23
    Soap
    0.22
    soap
    0.22
    xml
    0.20
     serial
    0.20
     Weather
    0.19
    _xml
    0.19
     storyline
    0.18
    Act Density 0.008%

    No Known Activations