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

    Neuronpedia

    INDEX
    Explanations

    phrases referring to specific individuals or groups

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals or entities in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yi
    -0.75
    edd
    -0.74
    hal
    -0.72
    PRESS
    -0.71
    DT
    -0.70
    pn
    -0.68
    yang
    -0.68
    MSN
    -0.68
    isp
    -0.68
    PL
    -0.67
    POSITIVE LOGITS
     ancestors
    1.09
     own
    1.01
     sole
    0.98
     namesake
    0.84
     grandparents
    0.84
     predecessors
    0.84
     parents
    0.82
     grandchildren
    0.81
     OWN
    0.79
     interests
    0.78
    Act Density 0.019%

    No Known Activations