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

    Neuronpedia

    INDEX
    Explanations

    adjectives indicating significance, importance, or value in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ekler
    -0.16
    íĻĪ
    -0.14
    .functions
    -0.13
    udies
    -0.13
    /scripts
    -0.13
    ories
    -0.13
    bjerg
    -0.13
    ektor
    -0.13
    arsity
    -0.13
    stants
    -0.13
    POSITIVE LOGITS
     enough
    0.35
     stuff
    0.34
     territory
    0.34
     fodder
    0.33
     advice
    0.32
     news
    0.32
     ammunition
    0.31
     evidence
    0.30
     medicine
    0.28
     terrain
    0.27
    Act Density 0.282%

    No Known Activations