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

    Neuronpedia

    INDEX
    Explanations

    the concept of "abuse" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ized
    -0.19
    comings
    -0.19
    stime
    -0.18
    abetic
    -0.18
    ruptcy
    -0.17
    payer
    -0.17
    noinspection
    -0.17
    leitung
    -0.17
    re
    -0.17
    st
    -0.17
    POSITIVE LOGITS
    normally
    0.24
    ject
    0.23
    stractions
    0.22
    iding
    0.21
    eer
    0.21
    ridged
    0.21
    eam
    0.20
    original
    0.20
    duct
    0.20
    e
    0.20
    Act Density 0.006%

    No Known Activations