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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the concept of commonality and status in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    stående
    -0.43
    geleitet
    -0.36
     ناش
    -0.36
    løs
    -0.36
    bergement
    -0.35
    modificar
    -0.35
     formed
    -0.35
    ambilan
    -0.34
     booth
    -0.34
     получил
    -0.34
    POSITIVE LOGITS
     modern
    0.57
     modernen
    0.54
    AutoScaleMode
    0.53
     meeste
    0.52
    ::_('
    0.51
     tartalomajánló
    0.51
     flesta
    0.50
     meisten
    0.49
    最近の
    0.48
     चीज़ों
    0.48
    Act Density 0.750%

    No Known Activations