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

    Neuronpedia

    INDEX
    Explanations

    historical and narrative elements in texts

    oai_token-act-pair · gpt-3.5-turbo

    instances of personal actions and events related to individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hub
    -0.78
    selves
    -0.78
    aura
    -0.72
     unison
    -0.69
    eps
    -0.69
     womb
    -0.68
     husbands
    -0.66
    avia
    -0.64
    common
    -0.63
    immune
    -0.63
    POSITIVE LOGITS
     himself
    1.45
     Himself
    0.90
     his
    0.83
     personally
    0.64
    panic
    0.64
     subordinates
    0.63
     remorse
    0.63
     wife
    0.63
     buddies
    0.62
     rall
    0.61
    Act Density 0.818%

    No Known Activations