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

    Neuronpedia

    INDEX
    Explanations

    references to characters or phrases indicating personal relationships and interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    脚注の使い方
    -0.89
     purpoſe
    -0.81
     itſelf
    -0.79
    UrlResolution
    -0.79
     himſelf
    -0.74
     متعلقه
    -0.74
     houſe
    -0.74
     reaſon
    -0.72
     themſelves
    -0.72
     difp
    -0.72
    POSITIVE LOGITS
     kasarigan
    0.50
     lắm
    0.47
     please
    0.45
     useContext
    0.45
    abetta
    0.44
    berger
    0.43
    hada
    0.42
     deep
    0.42
     putt
    0.42
    HDC
    0.42
    Act Density 0.061%

    No Known Activations