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

    Neuronpedia

    INDEX
    Explanations

    repetitions of the word "Per" indicating a focus on a specific individual or entity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    RIA
    -0.17
    .debian
    -0.15
    arse
    -0.15
    adder
    -0.15
    eld
    -0.15
    tempts
    -0.15
    umber
    -0.15
    itary
    -0.14
    wargs
    -0.14
    ark
    -0.14
    POSITIVE LOGITS
     capita
    0.24
    /per
    0.20
    iphery
    0.19
    pendicular
    0.19
    missive
    0.19
    mutations
    0.18
    empt
    0.18
    çħ
    0.17
    (per
    0.17
    malink
    0.17
    Act Density 0.028%

    No Known Activations