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

    Neuronpedia

    INDEX
    Explanations

    action-related phrases or keywords, for example "working together" or "beginning another breakthrough year."

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating actions and collaborations related to work and projects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    insula
    -0.55
     VIDEOS
    -0.54
    cuts
    -0.51
    Vers
    -0.49
    sheets
    -0.48
     datas
    -0.48
    doms
    -0.47
     Sierra
    -0.47
     Emails
    -0.46
    Sl
    -0.46
    POSITIVE LOGITS
    urated
    0.70
    enced
    0.66
    uble
    0.59
    uable
    0.59
    cerned
    0.57
    omorphic
    0.57
    ivated
    0.56
    zbek
    0.56
    ractical
    0.55
    actly
    0.55
    Act Density 3.594%

    No Known Activations