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

    Neuronpedia

    INDEX
    Explanations

    terminology associated with scientific explanations and theories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nad
    -0.16
    alama
    -0.15
    á»ijc
    -0.15
    lom
    -0.15
    оÑģÑĤÑĥп
    -0.15
    OffsetTable
    -0.14
    :System
    -0.14
    snap
    -0.14
    igh
    -0.14
    ÙĪÙĨا
    -0.14
    POSITIVE LOGITS
     models
    0.31
     explanation
    0.28
     predictions
    0.28
     explanations
    0.27
     Models
    0.26
     model
    0.25
     scenario
    0.25
     theories
    0.25
     theory
    0.25
    models
    0.24
    Act Density 0.163%

    No Known Activations