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

    Neuronpedia

    INDEX
    Explanations

    the word "king" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mazoo
    -0.74
    ValueStyle
    -0.72
     KA
    -0.71
     Ku
    -0.70
     KU
    -0.70
    újo
    -0.70
     K
    -0.69
    PerformLayout
    -0.67
    henswürdigkeiten
    -0.67
     KR
    -0.67
    POSITIVE LOGITS
    king
    1.52
    k
    1.45
    ked
    1.32
    ky
    1.21
    kin
    1.14
    ks
    1.12
    ker
    1.12
    ki
    1.06
    ken
    1.04
    kers
    1.02
    Act Density 0.177%

    No Known Activations