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

    Neuronpedia

    INDEX
    Explanations

    phrases that express skepticism or commentary on quality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    beros
    -0.15
    rtle
    -0.15
    .dds
    -0.15
    riot
    -0.14
    ÅĤaw
    -0.14
    ÑĦа
    -0.14
    isay
    -0.14
     SpoleÄį
    -0.14
    CCCCCC
    -0.14
    .dm
    -0.14
    POSITIVE LOGITS
    013
    0.17
    863
    0.16
    463
    0.15
     Newman
    0.14
     defeat
    0.14
     condition
    0.14
     Ning
    0.14
    958
    0.14
     Mog
    0.14
    id
    0.14
    Act Density 0.061%

    No Known Activations