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

    Neuronpedia

    INDEX
    Explanations

    phrases that begin with "The", particularly as they relate to describing or introducing concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    á»±
    -0.15
    uler
    -0.15
    stat
    -0.14
    ç·Ĵ
    -0.14
    inst
    -0.14
    las
    -0.14
     scratch
    -0.14
     vars
    -0.14
     scratched
    -0.13
    eno
    -0.13
    POSITIVE LOGITS
    erken
    0.16
    erif
    0.16
    imu
    0.16
    gnore
    0.15
    itsu
    0.15
    breadcrumb
    0.14
    ↵↵
    0.14
    olare
    0.14
    agem
    0.14
     Magnum
    0.14
    Act Density 0.447%

    No Known Activations