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

    Neuronpedia

    INDEX
    Explanations

    verbs and phrases related to work and productivity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /remove
    -0.35
    ings
    -0.32
    /disable
    -0.26
    /write
    -0.26
    /delete
    -0.24
    /close
    -0.21
    /change
    -0.21
    ÂŃing
    -0.21
    /do
    -0.21
    INGS
    -0.20
    POSITIVE LOGITS
    ly
    0.35
    /loading
    0.35
    redients
    0.33
    /testing
    0.33
    redient
    0.32
    ness
    0.29
    /logging
    0.28
    ton
    0.27
    -edge
    0.26
    enuity
    0.24
    Act Density 1.980%

    No Known Activations