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

    Neuronpedia

    INDEX
    Explanations

    references to historical analysis and documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pretty
    -0.23
     basically
    -0.23
     stuff
    -0.22
    plus
    -0.20
     plus
    -0.18
     get
    -0.18
     everybody
    -0.18
     really
    -0.18
    pretty
    -0.17
     totally
    -0.17
    POSITIVE LOGITS
     recieved
    0.19
    BaseContext
    0.16
    Additionally
    0.16
     Necessary
    0.15
     Additionally
    0.14
    å¡ij
    0.14
     proced
    0.14
    иÑĨин
    0.14
    ILLA
    0.14
    ระ
    0.14
    Act Density 0.404%

    No Known Activations