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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to semantics and logical structures in computational contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oon
    -0.16
     contradiction
    -0.16
    atica
    -0.15
    leo
    -0.14
     Improvement
    -0.14
     lease
    -0.13
    marsh
    -0.13
     Marsh
    -0.13
    ãĥ¼ãĥ©
    -0.13
    ea
    -0.13
    POSITIVE LOGITS
     natural
    0.26
     naturally
    0.23
    natural
    0.22
     Natural
    0.22
     studied
    0.20
    Natural
    0.20
     abstract
    0.19
     doÄŁal
    0.18
     Stud
    0.17
     notion
    0.17
    Act Density 0.101%

    No Known Activations