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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the abbreviation "KT" or variations thereof

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãģ¦
    -0.71
    ggies
    -0.61
    cean
    -0.61
    theless
    -0.60
    ption
    -0.59
    shire
    -0.58
    GROUND
    -0.58
     nudity
    -0.58
    phrine
    -0.58
    MpServer
    -0.57
    POSITIVE LOGITS
    ronics
    1.05
    omi
    1.00
    astic
    0.97
    omatic
    0.96
    ract
    0.96
    ropolis
    0.96
    ops
    0.96
    rop
    0.95
    ieth
    0.94
    raction
    0.94
    Act Density 0.008%

    No Known Activations