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

    Neuronpedia

    INDEX
    Explanations

    abbreviated phrases such as "Vis TA" or "Insp ir."

    oai_token-act-pair · gpt-3.5-turbo

    references to artistic or creative projects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     afterward
    -0.69
     respectively
    -0.67
     thereto
    -0.65
    )."
    -0.64
     downstream
    -0.61
    ]."
    -0.61
     anymore
    -0.60
     beforehand
    -0.60
     therein
    -0.59
    âĢ¦."
    -0.59
    POSITIVE LOGITS
     âĵĺ
    0.97
    tymology
    0.89
     Profile
    0.88
    ibliography
    0.88
    !:
    0.86
    iquette
    0.83
    udos
    0.79
    itars
    0.78
    isode
    0.77
    ':
    0.77
    Act Density 0.764%

    No Known Activations