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

    Neuronpedia

    INDEX
    Explanations

    phrases describing the act of recalling or remembering events or information

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "recalled."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    osphere
    -0.81
    arent
    -0.72
    alpha
    -0.72
    tan
    -0.69
    alach
    -0.68
    \\\\\\\\\\\\\\\\
    -0.68
    err
    -0.68
    cel
    -0.67
    htar
    -0.67
    opl
    -0.67
    POSITIVE LOGITS
     vividly
    1.04
     recalling
    0.95
     memories
    0.91
     nostalg
    0.86
     Remastered
    0.80
     recalled
    0.80
     recollection
    0.79
    Story
    0.74
     Memories
    0.73
     recalls
    0.72
    Act Density 0.019%

    No Known Activations