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

    Neuronpedia

    INDEX
    Explanations

    references to the act of removing or eliminating something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rap
    -0.16
    yt
    -0.15
    reg
    -0.15
    roll
    -0.15
    oning
    -0.14
    vos
    -0.14
    Ïģίζ
    -0.14
    udge
    -0.14
    ues
    -0.14
    loss
    -0.13
    POSITIVE LOGITS
    /add
    0.18
    erdale
    0.17
    /Add
    0.16
    /change
    0.16
    /edit
    0.16
    gross
    0.16
    /disable
    0.15
    /rem
    0.15
    /loose
    0.15
     khá»ıi
    0.15
    Act Density 0.049%

    No Known Activations