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

    Neuronpedia

    INDEX
    Explanations

    comparisons between different entities

    oai_token-act-pair · gpt-3.5-turbo

    references to comparisons and connections between entities or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĺħ
    -0.62
    enthal
    -0.50
    Discuss
    -0.50
    watching
    -0.49
    ©
    -0.49
     experimentation
    -0.47
    struction
    -0.47
     Mechdragon
    -0.47
     Giant
    -0.47
     Oaks
    -0.47
    POSITIVE LOGITS
     dots
    1.34
     to
    0.91
    MpServer
    0.88
     toget
    0.87
     closely
    0.80
     thereto
    0.76
     favorably
    0.75
     together
    0.73
     directly
    0.72
     securely
    0.71
    Act Density 0.203%

    No Known Activations