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

    Neuronpedia

    INDEX
    Explanations

    names of characters and key relationships in a storyline

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    priv
    -0.15
    424
    -0.14
    çĽ
    -0.14
     armored
    -0.14
    occo
    -0.14
    rab
    -0.13
     volunt
    -0.13
     subrange
    -0.13
    423
    -0.13
    obi
    -0.13
    POSITIVE LOGITS
     soap
    0.27
     Soap
    0.25
    Soap
    0.21
    soap
    0.21
     Coron
    0.21
     Em
    0.20
     Weather
    0.19
     Cain
    0.19
     serial
    0.19
     ITV
    0.18
    Act Density 0.007%

    No Known Activations