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

    Neuronpedia

    INDEX
    Explanations

    references to the act of cutting or its related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    czy
    -0.20
    hu
    -0.19
    636
    -0.18
    kes
    -0.16
    opa
    -0.16
    mma
    -0.16
    esk
    -0.15
    ilerden
    -0.15
    oles
    -0.15
    aud
    -0.15
    POSITIVE LOGITS
    tings
    0.37
    throat
    0.35
    aneous
    0.35
    ting
    0.33
    ters
    0.32
     corners
    0.28
    back
    0.28
    -edge
    0.27
    backs
    0.27
     down
    0.25
    Act Density 0.041%

    No Known Activations