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

    Neuronpedia

    INDEX
    Explanations

    references to classes and IDs in programming or markup languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     NavParams
    -0.15
    /../
    -0.14
    iera
    -0.14
    .IsNullOr
    -0.14
    ixe
    -0.14
    rias
    -0.14
    beck
    -0.14
     Warning
    -0.14
    draul
    -0.14
    omorphic
    -0.13
    POSITIVE LOGITS
     Removal
    0.15
    ovit
    0.15
     slow
    0.15
     atop
    0.14
    ÄĽnÃŃ
    0.14
    sg
    0.14
     amb
    0.14
     Progressive
    0.13
    ilib
    0.13
    éĽ²
    0.13
    Act Density 0.043%

    No Known Activations