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

    Neuronpedia

    INDEX
    Explanations

    words related to the foundation or fundamental principle of something

    oai_token-act-pair · gpt-3.5-turbo

    references to foundational concepts or underlying principles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    opers
    -0.92
    oho
    -0.77
    oping
    -0.76
     Wend
    -0.74
    wagen
    -0.72
    quer
    -0.70
    ipop
    -0.68
    apes
    -0.68
    osen
    -0.68
    cha
    -0.68
    POSITIVE LOGITS
     basis
    0.87
     thereof
    0.79
    plates
    0.77
     underpin
    0.77
    Goal
    0.74
     foundation
    0.72
     footing
    0.72
    INAL
    0.68
    rastructure
    0.68
     grounding
    0.67
    Act Density 0.024%

    No Known Activations