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

    Neuronpedia

    INDEX
    Explanations

    the occurrence of the word "single" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    akings
    -0.91
    apons
    -0.85
    Downloadha
    -0.82
    ooks
    -0.77
    UFF
    -0.76
    olas
    -0.76
    raints
    -0.74
    ours
    -0.74
    soDeliveryDate
    -0.72
    emis
    -0.69
    POSITIVE LOGITS
    handedly
    1.19
     digit
    1.04
    ton
    1.02
     piece
    1.00
     person
    0.95
     digits
    0.93
     minded
    0.88
     molecule
    0.87
     sided
    0.87
     minute
    0.86
    Act Density 0.020%

    No Known Activations