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

    Neuronpedia

    INDEX
    Explanations

    references to collars, including types and descriptions of their features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    collar and collateral

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    بوابة
    -0.41
     Rep
    -0.40
     Dede
    -0.39
    évaluateur
    -0.38
    dealing
    -0.38
    vk
    -0.37
     grava
    -0.36
     panoramique
    -0.36
    avance
    -0.35
    ͙
    -0.35
    POSITIVE LOGITS
    Collar
    0.74
     Collar
    0.69
     collar
    0.68
    :✨
    0.64
    rungsseite
    0.59
     collars
    0.59
     RouterModule
    0.57
    ConstraintMaker
    0.57
    collar
    0.54
     }{@
    0.53
    Act Density 0.005%

    No Known Activations