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

    Neuronpedia

    INDEX
    Explanations

    references to the "Next Generation" or similar sequential concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abler
    -0.18
    uten
    -0.16
    ician
    -0.15
    ishments
    -0.15
    ilate
    -0.15
    aghan
    -0.15
    rift
    -0.14
    wers
    -0.14
    head
    -0.14
    defaults
    -0.14
    POSITIVE LOGITS
    door
    0.25
     door
    0.21
    -generation
    0.20
    -door
    0.19
    ernal
    0.19
    GEN
    0.19
     Generation
    0.17
     week
    0.17
    -gen
    0.16
    ural
    0.16
    Act Density 0.028%

    No Known Activations