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

    Neuronpedia

    INDEX
    Explanations

    references to serialized content or structured series

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ama
    -0.15
    692
    -0.15
    abyrin
    -0.14
    832
    -0.13
     jist
    -0.13
    642
    -0.13
    847
    -0.13
    XS
    -0.13
     Insight
    -0.13
    ìĥĪ
    -0.13
    POSITIVE LOGITS
     Part
    0.45
    Part
    0.37
     part
    0.37
     PART
    0.35
     Parts
    0.33
    PART
    0.33
    part
    0.31
     series
    0.30
    _part
    0.30
    -part
    0.30
    Act Density 0.072%

    No Known Activations