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

    Neuronpedia

    INDEX
    Explanations

    concepts related to data formatting and information structuring

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Bewußt
    -0.65
     müſſen
    -0.51
    Egypte
    -0.49
    adeloupe
    -0.48
     помню
    -0.47
    视角
    -0.47
    sphase
    -0.46
     übersch
    -0.45
    ędziesz
    -0.45
     ſeine
    -0.45
    POSITIVE LOGITS
     Numerade
    0.48
    Personendaten
    0.46
     betweenstory
    0.45
     JpaRepository
    0.43
    等等
    0.42
     ModelExpression
    0.40
    WindowConstants
    0.40
    0.40
     怎样
    0.40
     PeEnEo
    0.39
    Act Density 0.008%

    No Known Activations