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

    Neuronpedia

    INDEX
    Explanations

    highly impactful or significant moments or elements

    oai_token-act-pair · gpt-3.5-turbo

    references to memorable or unforgettable experiences or characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sterdam
    -0.82
    ©¶æ
    -0.81
    chens
    -0.75
    galitarian
    -0.72
    eeks
    -0.71
    hop
    -0.70
    krit
    -0.70
    raised
    -0.70
    olen
    -0.69
     uninsured
    -0.69
    POSITIVE LOGITS
     memorable
    1.08
     unforgettable
    0.98
     memories
    0.97
     moments
    0.93
     experiences
    0.86
    lihood
    0.84
     remem
    0.82
    Story
    0.82
    theless
    0.81
     Moments
    0.77
    Act Density 0.014%

    No Known Activations