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

    Neuronpedia

    INDEX
    Explanations

    references to a specific location named "Per"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the token "Per."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    MpServer
    -0.71
    INESS
    -0.70
    aiden
    -0.68
     pneum
    -0.68
     Lazarus
    -0.67
    DERR
    -0.67
    ATIONAL
    -0.64
    naires
    -0.62
     dwar
    -0.62
    å¸
    -0.61
    POSITIVE LOGITS
    cussion
    1.36
    ceptions
    1.27
    ipher
    1.27
    uvian
    1.27
    secut
    1.27
    forming
    1.26
    malink
    1.26
    secution
    1.20
    ceived
    1.18
    imeter
    1.17
    Act Density 0.021%

    No Known Activations