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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating purpose or intended actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    utenberg
    -0.17
     çĭ
    -0.16
    fox
    -0.15
    occan
    -0.15
     éĸ
    -0.14
    ighthouse
    -0.14
    tha
    -0.14
    latlong
    -0.13
    acco
    -0.13
    ventus
    -0.13
    POSITIVE LOGITS
    ÙĦØŃ
    0.16
    รà¸ĩ
    0.15
    íĪ¬
    0.14
    mî
    0.14
    å¿ł
    0.14
    abis
    0.14
    ãģĵãģĿ
    0.13
    353
    0.13
     mass
    0.13
    ValueCollection
    0.13
    Act Density 0.020%

    No Known Activations