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

    Neuronpedia

    INDEX
    Explanations

    words related to historical events and names

    oai_token-act-pair · gpt-3.5-turbo

    connections between thoughts and experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .[
    -0.81
    .
    -0.77
    .–
    -0.76
    ;
    -0.76
    .","
    -0.72
    .''.
    -0.72
    ãĢĤ
    -0.68
    ."[
    -0.68
    ."
    -0.68
    .''
    -0.67
    POSITIVE LOGITS
    ctive
    0.55
    isations
    0.47
    izens
    0.46
    Scotland
    0.43
    ctory
    0.43
    ws
    0.43
     Sundays
    0.43
    ifts
    0.43
     Fulton
    0.43
    izations
    0.42
    Act Density 2.128%

    No Known Activations