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

    Neuronpedia

    INDEX
    Explanations

    phrases relating to planning, collaboration, and outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     suppress
    -0.17
     cultivation
    -0.15
    Editing
    -0.15
    elling
    -0.15
    rippling
    -0.15
     cultivated
    -0.14
    Parsing
    -0.14
     cultiv
    -0.14
     obl
    -0.14
     cultivating
    -0.14
    POSITIVE LOGITS
     making
    0.33
     having
    0.32
     taking
    0.29
     getting
    0.28
     doing
    0.28
     putting
    0.27
     setting
    0.26
     being
    0.26
     bury
    0.25
     bas
    0.25
    Act Density 2.966%

    No Known Activations