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

    Neuronpedia

    INDEX
    Explanations

    titles or roles associated with leadership or authority

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals holding directorial positions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     compr
    -0.66
    theless
    -0.66
     msec
    -0.59
     silicone
    -0.58
     Leafs
    -0.58
    asions
    -0.58
    ACE
    -0.57
     bras
    -0.57
     rive
    -0.57
    WOR
    -0.57
    POSITIVE LOGITS
    ial
    1.07
    ovie
    1.00
    ially
    1.00
    ials
    0.97
    ates
    0.89
    ate
    0.89
    RECT
    0.85
    IAL
    0.84
    ogen
    0.81
    itatively
    0.81
    Act Density 0.037%

    No Known Activations