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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "taken" and its variations, often in the context of gathering or summarizing information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     antaranya
    -0.85
     gioia
    -0.81
    salud
    -0.76
     stället
    -0.74
    warnai
    -0.73
    erty
    -0.73
     helst
    -0.73
     wikipagina
    -0.71
    bbene
    -0.70
     Gegenteil
    -0.68
    POSITIVE LOGITS
     flown
    1.09
    eken
    1.07
     taken
    1.03
    fallen
    1.00
     seen
    0.98
     risen
    0.96
    seen
    0.96
     Seen
    0.95
    >`
    0.95
     spoken
    0.95
    Act Density 0.130%

    No Known Activations