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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns combined with verbs related to actions and decision-making

    oai_token-act-pair · gpt-3.5-turbo

    indicators of emotional or relational commitment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alez
    -0.71
    pedia
    -0.71
    sonian
    -0.68
    hower
    -0.68
    lins
    -0.67
    neapolis
    -0.67
     Hearth
    -0.65
     KH
    -0.65
    meyer
    -0.64
    psons
    -0.63
    POSITIVE LOGITS
    forth
    0.71
     regretted
    0.64
     somehow
    0.64
     "âĢ¦
    0.61
     substit
    0.61
     nevertheless
    0.61
     outwe
    0.61
     discriminated
    0.61
    Catal
    0.60
     substituted
    0.60
    Act Density 0.593%

    No Known Activations