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

    Neuronpedia

    INDEX
    Explanations

    mentions of artificial intelligence performing tasks

    oai_token-act-pair · gpt-3.5-turbo

    references to artificial intelligence and its functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    çīĪ
    -0.83
    ospons
    -0.81
    enture
    -0.80
    soType
    -0.79
    archives
    -0.76
    ¬¼
    -0.72
     srfAttach
    -0.72
     Membership
    -0.71
     Arms
    -0.70
    itutional
    -0.69
    POSITIVE LOGITS
     detect
    1.42
     detects
    1.35
     detecting
    1.20
     automatically
    1.19
    Detect
    1.17
     Detect
    1.15
     algorithms
    1.13
     optimize
    1.12
     algorithm
    1.11
     scan
    1.05
    Act Density 0.378%

    No Known Activations