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

    Neuronpedia

    INDEX
    Explanations

    names of individuals

    oai_token-act-pair · gpt-3.5-turbo

    the name "Jake" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     conduc
    -0.78
    amera
    -0.70
    iary
    -0.69
    iated
    -0.68
     subst
    -0.66
    inals
    -0.65
    arily
    -0.65
    ributed
    -0.64
    inances
    -0.64
     glim
    -0.63
    POSITIVE LOGITS
    glers
    0.94
     Jake
    0.89
    unin
    0.83
     Gy
    0.83
    imaru
    0.82
     Skywalker
    0.81
    EStream
    0.79
    ango
    0.77
    warm
    0.77
    ansas
    0.76
    Act Density 0.012%

    No Known Activations