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

    Neuronpedia

    INDEX
    Explanations

    words related to specific and varied topics, such as people (like Ronda Rousey), food (like pie crust), technology (like Nvidia), and scientific terms (like quarks)

    oai_token-act-pair · gpt-3.5-turbo

    words related to various measurements or quantities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    TN
    -0.73
     Alam
    -0.70
    IJ
    -0.67
    ARDIS
    -0.64
     Scand
    -0.64
     EW
    -0.64
     Nem
    -0.63
     Kes
    -0.62
    ISON
    -0.62
     Leban
    -0.62
    POSITIVE LOGITS
    omial
    0.89
    spir
    0.87
    matic
    0.81
    stro
    0.79
    dust
    0.77
    boarding
    0.75
    ldom
    0.75
    osexual
    0.73
    ctrl
    0.73
    punk
    0.73
    Act Density 0.237%

    No Known Activations