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

    Neuronpedia

    INDEX
    Explanations

    references to the past or nostalgia

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Larsen
    -0.95
    %)$
    -0.92
    tershire
    -0.88
    °•
    -0.86
    __":
    -0.86
     Winaray
    -0.84
    isor
    -0.83
    urethane
    -0.83
    ricane
    -0.81
    aarrggbb
    -0.80
    POSITIVE LOGITS
    Back
    1.33
     Back
    1.32
    back
    1.29
    BACK
    1.26
     back
    1.24
     BACK
    1.21
     backs
    1.03
     indietro
    0.96
    backs
    0.94
    btnBack
    0.94
    Act Density 0.072%

    No Known Activations