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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to various locations or individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to specific locations or names associated with "Sav."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    WAYS
    -0.73
    âĸ¬âĸ¬
    -0.73
    matically
    -0.72
     threaded
    -0.71
    anguage
    -0.69
    Reloaded
    -0.68
     inclined
    -0.67
     bom
    -0.66
     proximity
    -0.65
    hower
    -0.65
    POSITIVE LOGITS
    inelli
    1.05
    ille
    1.01
    vy
    0.96
    icz
    0.93
    arella
    0.93
    elin
    0.92
    itri
    0.89
    anas
    0.88
    chenko
    0.88
    atz
    0.85
    Act Density 0.016%

    No Known Activations