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

    Neuronpedia

    INDEX
    Explanations

    technical terms or code-related strings

    oai_token-act-pair · gpt-3.5-turbo

    references to supporters and community engagement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ModLoader
    -0.76
    ãĥ¯ãĥ³
    -0.74
    代
    -0.69
    åĪ
    -0.69
    ãĤ¨ãĥ«
    -0.68
     Bun
    -0.64
    天
    -0.64
    ãĥķãĤ©
    -0.64
    ãĤ®
    -0.62
    é¾įå¥ij士
    -0.62
    POSITIVE LOGITS
    lege
    0.81
    irs
    0.80
    asury
    0.78
    etts
    0.74
    iry
    0.72
    iencies
    0.72
    ighed
    0.71
    romeda
    0.71
    ovy
    0.70
    ·
    0.70
    Act Density 0.322%

    No Known Activations