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

    Neuronpedia

    INDEX
    Explanations

    terms related to mechanical structures or systems

    oai_token-act-pair · gpt-3.5-turbo

    technical terms related to mechanisms and their functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iaries
    -0.91
    apest
    -0.76
    iary
    -0.74
     Oval
    -0.72
    upon
    -0.69
    fig
    -0.68
    worthy
    -0.68
    lihood
    -0.66
    onga
    -0.66
     TAMADRA
    -0.66
    POSITIVE LOGITS
     mechanism
    0.91
    witz
    0.88
     Mechan
    0.87
     whereby
    0.87
     workings
    0.85
     mechanisms
    0.82
    ror
    0.80
     fracturing
    0.77
    ulic
    0.74
    utics
    0.72
    Act Density 0.069%

    No Known Activations