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

    Neuronpedia

    INDEX
    Explanations

    references to patents and inventions

    oai_token-act-pair · gpt-3.5-turbo

    references to entities, particularly people or organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    side
    -0.83
    udeb
    -0.80
    ãĥĥãĤ¯
    -0.76
    ãĤ§
    -0.73
    top
    -0.73
    ãĤ¨ãĥ«
    -0.70
    lake
    -0.68
    vertisement
    -0.68
    atform
    -0.68
    electric
    -0.66
    POSITIVE LOGITS
    ailed
    0.91
    iates
    0.88
    ails
    0.83
    ented
    0.81
    acles
    0.81
    ents
    0.80
    ucky
    0.78
    ropy
    0.78
    enses
    0.76
    ail
    0.75
    Act Density 0.029%

    No Known Activations