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

    Neuronpedia

    INDEX
    Explanations

    the prefix "ob" followed by a 9 or 10

    oai_token-act-pair · gpt-3.5-turbo

    references to objects or entities that start with the letters "ob"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     guiActiveUnfocused
    -0.92
    EngineDebug
    -0.82
     Michaels
    -0.76
    agne
    -0.75
     gas
    -0.74
     Birch
    -0.71
    ivities
    -0.68
     Carlson
    -0.67
    WT
    -0.63
    UES
    -0.62
    POSITIVE LOGITS
    lique
    1.45
    solete
    1.25
    livion
    1.23
    fusc
    1.22
    amacare
    1.21
    nox
    1.20
    vious
    1.20
    structed
    1.19
    eyed
    1.17
    taining
    1.16
    Act Density 0.023%

    No Known Activations