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

    Neuronpedia

    INDEX
    Explanations

    actions related to financial transactions and social interactions

    oai_token-act-pair · gpt-3.5-turbo

    actions and behaviors related to social connections and interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    croft
    -0.76
    alon
    -0.69
    appa
    -0.68
    romeda
    -0.68
    sama
    -0.68
    ç«
    -0.66
    Parameter
    -0.66
    affer
    -0.65
    çĶ°
    -0.65
    718
    -0.65
    POSITIVE LOGITS
     themselves
    1.11
     their
    0.98
     Their
    0.86
     THEIR
    0.85
     collectively
    0.80
     diets
    0.79
     increasingly
    0.78
     wives
    0.74
    their
    0.73
     extinct
    0.73
    Act Density 0.670%

    No Known Activations