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

    Neuronpedia

    INDEX
    Explanations

    references to returning or going back

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    :✨
    -0.84
     Larsen
    -0.82
     Larson
    -0.80
    λία
    -0.80
    %)$
    -0.78
    CMA
    -0.77
    ряда
    -0.73
    °•
    -0.73
    MeasureSpec
    -0.73
     Goya
    -0.72
    POSITIVE LOGITS
     back
    1.83
    back
    1.76
     Back
    1.74
    Back
    1.74
    BACK
    1.68
     BACK
    1.65
     backs
    1.35
    backs
    1.25
     zurück
    1.20
     indietro
    1.18
    Act Density 0.052%

    No Known Activations