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

    Neuronpedia

    INDEX
    Explanations

    combinations of shapes and numerical references related to actions or objects within a structured system

    oai_token-act-pair · gpt-3.5-turbo

    elements related to visual representation and organization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Relief
    -0.71
     Brotherhood
    -0.65
    Leaks
    -0.63
     Canary
    -0.61
     Jihad
    -0.61
     Arab
    -0.60
     Executive
    -0.60
     Expedition
    -0.59
     Nightmares
    -0.59
     Lieberman
    -0.59
    POSITIVE LOGITS
    mith
    1.37
    paces
    1.29
    pace
    1.26
    pring
    1.22
    hip
    1.21
    hips
    1.11
    ynthesis
    1.10
    cale
    1.08
    poons
    1.03
    peed
    1.03
    Act Density 0.604%

    No Known Activations