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

    Neuronpedia

    INDEX
    Explanations

    instances where the word "plan" is mentioned with a high degree of relevance

    oai_token-act-pair · gpt-3.5-turbo

    references to plans or strategic proposals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Naz
    -0.62
     Trophy
    -0.61
     dab
    -0.60
     ILCS
    -0.60
     Figures
    -0.59
     disbelief
    -0.59
    ï¸ı
    -0.59
    athi
    -0.58
     Stain
    -0.58
     charism
    -0.56
    POSITIVE LOGITS
    emaker
    1.10
    isphere
    1.03
    ters
    0.95
    etary
    0.87
    ks
    0.87
    ologies
    0.85
    meal
    0.84
    escape
    0.82
    urally
    0.82
    ter
    0.82
    Act Density 0.064%

    No Known Activations