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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "single" followed by a number indicating strength or quantity

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "single."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    akings
    -0.96
    apons
    -0.83
    Downloadha
    -0.77
    ooks
    -0.76
    acements
    -0.75
    ours
    -0.74
     Hoo
    -0.72
    vu
    -0.72
    raints
    -0.72
    orsi
    -0.71
    POSITIVE LOGITS
    handedly
    1.17
     digit
    1.07
    ton
    0.94
     piece
    0.93
     person
    0.92
     minute
    0.89
     digits
    0.87
     molecule
    0.87
    player
    0.85
     sided
    0.84
    Act Density 0.022%

    No Known Activations