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

    Neuronpedia

    INDEX
    Explanations

    topics of discussion or conversation

    oai_token-act-pair · gpt-3.5-turbo

    references to various subjects or themes being discussed

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     rush
    -0.66
    ANY
    -0.61
     Rouge
    -0.61
    uin
    -0.60
    berto
    -0.60
    rection
    -0.60
     claw
    -0.60
     rip
    -0.59
    NEY
    -0.58
    pex
    -0.58
    POSITIVE LOGITS
     topics
    3.64
     Topics
    2.52
     topic
    2.36
     subjects
    1.97
     themes
    1.86
    Topics
    1.75
    topic
    1.68
     Topic
    1.62
    Topic
    1.59
     questions
    1.58
    Act Density 0.017%

    No Known Activations