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

    Neuronpedia

    INDEX
    Explanations

    gerunds and participles, indicating ongoing actions or processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /remove
    -0.26
    ings
    -0.20
    /write
    -0.20
    sv
    -0.19
    /delete
    -0.18
    ÂŃing
    -0.18
    /close
    -0.18
    tings
    -0.17
    /disable
    -0.17
    ses
    -0.16
    POSITIVE LOGITS
    ly
    0.30
    redient
    0.28
    redients
    0.27
    ton
    0.27
    hausen
    0.25
    tons
    0.24
    AME
    0.24
    enuity
    0.24
    /loading
    0.23
    gg
    0.22
    Act Density 2.043%

    No Known Activations