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

    Neuronpedia

    INDEX
    Explanations

    instances of discussions or changes of subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ovit
    -0.14
    adio
    -0.14
    ÑģÑĤÑĢ
    -0.14
    leme
    -0.14
    pline
    -0.14
    ãģİ
    -0.13
    braco
    -0.13
    .cms
    -0.13
    ourt
    -0.13
    è¨ĪåĬĥ
    -0.12
    POSITIVE LOGITS
     topic
    1.13
     subject
    1.10
    subject
    0.88
    topic
    0.87
     Topic
    0.87
     topics
    0.85
     Subject
    0.83
    Topic
    0.81
    Subject
    0.80
     subjects
    0.80
    Act Density 0.230%

    No Known Activations