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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or names related to a particular individual

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Strong" in relation to violent events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     externalToEVAOnly
    -0.84
    apter
    -0.76
     è£ıç
    -0.72
    å¹
    -0.68
    opus
    -0.67
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.66
    illon
    -0.66
    utory
    -0.65
    mits
    -0.64
    uracy
    -0.63
    POSITIVE LOGITS
    itudinal
    1.12
    er
    1.01
    est
    0.90
    ly
    0.88
    enger
    0.87
    erness
    0.85
    ingham
    0.85
    ings
    0.81
    edo
    0.81
    fast
    0.80
    Act Density 0.024%

    No Known Activations