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

    Neuronpedia

    INDEX
    Explanations

    mentions of certifications or organizational acronyms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ppo
    -0.19
    len
    -0.19
    roc
    -0.18
    os
    -0.18
    per
    -0.18
    la
    -0.17
    ло
    -0.17
    oses
    -0.17
    ORT
    -0.17
    poser
    -0.17
    POSITIVE LOGITS
    ocked
    0.20
     rov
    0.17
    ault
    0.16
    egl
    0.16
    ess
    0.16
    ogh
    0.16
    еп
    0.14
    opts
    0.14
    oram
    0.14
    VID
    0.14
    Act Density 0.060%

    No Known Activations