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

    Neuronpedia

    INDEX
    Explanations

    verbs indicating physical actions being carried out by individuals

    oai_token-act-pair · gpt-3.5-turbo

    gerunds and action-related terms that describe clothing and accessories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    agonist
    -0.81
    urden
    -0.79
    ãĤ´
    -0.72
    bsite
    -0.72
    src
    -0.71
    alloc
    -0.70
    ãĥĦ
    -0.68
    ubuntu
    -0.68
    terday
    -0.67
    pection
    -0.67
    POSITIVE LOGITS
     careers
    1.26
     histories
    1.23
     varying
    1.22
     respective
    1.18
     similar
    1.17
     portfolios
    1.16
     backgrounds
    1.15
     themselves
    1.12
     their
    1.12
     agendas
    1.07
    Act Density 0.545%

    No Known Activations