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

    Neuronpedia

    INDEX
    Explanations

    terms related to ethical practices and considerations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    stad
    -0.17
    .LayoutParams
    -0.15
    asz
    -0.15
    oci
    -0.14
    lightbox
    -0.14
    igkeit
    -0.14
    erken
    -0.14
    EMP
    -0.14
    earth
    -0.14
    igel
    -0.14
    POSITIVE LOGITS
    ereal
    0.28
    ylene
    0.25
    moid
    0.25
    ically
    0.24
    ical
    0.24
    ics
    0.21
    noc
    0.20
    ICS
    0.20
    ICAL
    0.19
    erten
    0.18
    Act Density 0.015%

    No Known Activations