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

    Neuronpedia

    INDEX
    Explanations

    phrases related to discussions on various topics, including justice, religion, politics, and music

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating opinions or assertions about various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ulia
    -0.79
    uld
    -0.73
    usercontent
    -0.71
     throats
    -0.71
    xxxx
    -0.67
    inav
    -0.66
    Scroll
    -0.64
    votes
    -0.63
    yrim
    -0.63
    xxxxxxxx
    -0.62
    POSITIVE LOGITS
     aimed
    1.18
     geared
    1.17
     akin
    1.09
     designed
    1.09
     intended
    1.08
     rooted
    1.06
     about
    1.05
     focused
    1.04
     concerned
    1.02
     comprised
    1.02
    Act Density 0.440%

    No Known Activations