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

    Neuronpedia

    INDEX
    Explanations

    concepts related to policies and organizational structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    agues
    -0.18
    .fhir
    -0.16
    /misc
    -0.15
    kins
    -0.14
    awns
    -0.14
    ongs
    -0.14
    ilos
    -0.14
     Pitch
    -0.14
     crib
    -0.14
    yor
    -0.14
    POSITIVE LOGITS
    па
    0.15
    enda
    0.15
    ectomy
    0.15
    chie
    0.14
    ets
    0.13
    ephy
    0.13
    erase
    0.13
    833
    0.13
    ye
    0.13
    ple
    0.13
    Act Density 0.189%

    No Known Activations