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

    Neuronpedia

    INDEX
    Explanations

    references to characters or names, particularly initials or single letters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     dealing
    -0.74
     renamed
    -0.73
     tackling
    -0.73
     costing
    -0.71
     1600
    -0.70
     proving
    -0.69
     bottleneck
    -0.67
     legacy
    -0.66
     retina
    -0.66
     equivalent
    -0.65
    POSITIVE LOGITS
    aiman
    1.19
    uy
    1.14
    assi
    1.07
    aim
    1.07
    antz
    1.07
    aley
    1.06
    ahl
    1.05
    essler
    1.04
    FI
    1.04
    elli
    1.02
    Act Density 0.106%

    No Known Activations