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

    Neuronpedia

    INDEX
    Explanations

    items related to lists and organizational structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ########.
    -0.67
    はじめに
    -0.43
    FileDescriptor
    -0.43
     Afric
    -0.42
     NIP
    -0.42
     використо
    -0.40
     Plantation
    -0.40
    MockBean
    -0.40
    rainian
    -0.40
    CodedInputStream
    -0.40
    POSITIVE LOGITS
     dust
    0.75
    ol
    0.75
     ol
    0.69
     dusty
    0.67
     Dust
    0.67
    dust
    0.66
    Dust
    0.66
     Ol
    0.66
    intelligence
    0.65
     intelligence
    0.62
    Act Density 0.321%

    No Known Activations