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

    Neuronpedia

    INDEX
    Explanations

    words related to acts of recalling or remembering

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the prefix "rec," typically indicating something that is returned, repeated, or related to recovery

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    furt
    -0.82
    MENTS
    -0.79
    OPLE
    -0.72
    loo
    -0.72
    nuts
    -0.71
     Masters
    -0.70
    )=(
    -0.70
    MENT
    -0.69
     Welsh
    -0.69
    bags
    -0.68
    POSITIVE LOGITS
    onduct
    1.06
    ievers
    1.04
    ieved
    1.00
    ourses
    1.00
    ategor
    1.00
    uters
    0.99
    occ
    0.99
    secut
    0.99
    ursion
    0.99
    urrence
    0.99
    Act Density 0.007%

    No Known Activations