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

    Neuronpedia

    INDEX
    Explanations

    expressions related to locations and dates

    oai_token-act-pair · gpt-3.5-turbo

    elements related to aging and age-related context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vard
    -0.72
    ramid
    -0.67
    ipt
    -0.65
    izen
    -0.61
    odan
    -0.58
    vae
    -0.57
     Tome
    -0.55
    eele
    -0.54
    undai
    -0.54
    odge
    -0.54
    POSITIVE LOGITS
     so
    1.19
    so
    1.07
     Therefore
    1.06
     hence
    1.06
    Therefore
    1.05
     meaning
    1.04
    yet
    1.01
    So
    0.99
     So
    0.97
     therefore
    0.91
    Act Density 0.945%

    No Known Activations