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

    Neuronpedia

    INDEX
    Explanations

    names and phrases indicating personal relationships or interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    indow
    -0.15
    _GENERIC
    -0.15
     hood
    -0.14
    ilip
    -0.14
    -widgets
    -0.14
    .rb
    -0.14
    inel
    -0.14
    Ìģt
    -0.14
    èĩ
    -0.14
    ipt
    -0.14
    POSITIVE LOGITS
    chie
    0.18
     Vic
    0.17
    astle
    0.15
     gen
    0.15
    ibs
    0.15
    antan
    0.14
     ’
    0.14
    ãģ¡ãĤĥãĤĵ
    0.14
     brother
    0.14
     Brother
    0.14
    Act Density 0.310%

    No Known Activations