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

    Neuronpedia

    INDEX
    Explanations

    phrases related to scientific studies and findings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    jface
    -0.58
     <=",
    -0.55
     nemlig
    -0.53
    transQ
    -0.53
     >=",
    -0.52
    sätzlich
    -0.49
    脚注の使い方
    -0.49
    Personendaten
    -0.48
     esternos
    -0.47
     ModelExpression
    -0.47
    POSITIVE LOGITS
    tadır
    0.68
     insuffisamment
    0.66
    providedIn
    0.65
    }$.\\
    0.65
    StoreMessageInfo
    0.59
    <eos>
    0.58
    drawSprites
    0.57
    SPJ
    0.57
     übrigens
    0.56
     Chernobyl
    0.55
    Act Density 0.310%

    No Known Activations