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

    Neuronpedia

    INDEX
    Explanations

    phrases related to classified information or sensitive topics

    oai_token-act-pair · gpt-3.5-turbo

    terms related to secrecy and security

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Natural
    -0.70
     Weston
    -0.68
    SHIP
    -0.63
     Photographer
    -0.59
    Japanese
    -0.56
     Lomb
    -0.55
    hess
    -0.55
    ciplinary
    -0.55
     ));
    -0.55
     Holden
    -0.54
    POSITIVE LOGITS
    »
    1.13
    [/
    1.00
    ãĢı
    0.99
    ãĢį
    0.97
    \)
    0.94
    ''
    0.92
    ,''
    0.89
    _.
    0.86
    ãĢij
    0.85
    `,
    0.84
    Act Density 0.855%

    No Known Activations