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

    Neuronpedia

    INDEX
    Explanations

    references to letters and letter-related terminology in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ########.
    -0.94
     surla
    -0.86
    -0.86
    parsedMessage
    -0.85
    ImageContext
    -0.83
    principalColumn
    -0.82
    UserScript
    -0.79
     queſta
    -0.79
     iNdEx
    -0.77
    +#+#
    -0.77
    POSITIVE LOGITS
     capabilities
    0.89
     capability
    0.84
     prospects
    0.81
     Letter
    0.75
    Letter
    0.71
     capacities
    0.66
     capacity
    0.66
     capa
    0.66
    letter
    0.64
     Letters
    0.64
    Act Density 0.297%

    No Known Activations