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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, particularly names of people and places

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     kasarigan
    -0.61
    المناصب
    -0.51
    AccessorTable
    -0.47
    ]++;
    -0.47
     אותו
    -0.47
     EnglishChoose
    -0.47
    urlopen
    -0.46
     상세
    -0.45
    のですね
    -0.44
     थी
    -0.44
    POSITIVE LOGITS
    ########.
    0.96
     MonoBehaviour
    0.73
     GenerationType
    0.71
    ArgsConstructor
    0.68
     صوتيه
    0.67
     NSCoder
    0.64
    contentLoaded
    0.63
     onAnimation
    0.62
    extAlignment
    0.61
    fromnode
    0.61
    Act Density 0.446%

    No Known Activations