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

    Neuronpedia

    INDEX
    Explanations

    references to political controversies and criticisms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    otlin
    -0.15
    pector
    -0.14
    ekim
    -0.14
    aris
    -0.14
    ilde
    -0.14
     Gone
    -0.14
    mite
    -0.14
    ucha
    -0.14
    ucken
    -0.14
    asz
    -0.13
    POSITIVE LOGITS
     quarters
    0.24
     detr
    0.24
     academics
    0.23
     critics
    0.21
     voices
    0.21
     column
    0.21
     opponents
    0.21
     some
    0.21
     segments
    0.20
     prominent
    0.20
    Act Density 0.460%

    No Known Activations