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

    Neuronpedia

    INDEX
    Explanations

    adjectives and descriptive phrases conveying quality or characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     fraî
    -0.73
     sī
    -0.68
     [],
    -0.67
    räck
    -0.66
     تضيفلها
    -0.66
    __":
    -0.66
     تانيه
    -0.66
     quæ
    -0.65
    ="#"><
    -0.65
    )="
    -0.64
    POSITIVE LOGITS
    非常好
    0.64
    Very
    0.60
     Very
    0.58
     very
    0.57
    ftagPool
    0.56
     جدًا
    0.55
     sekali
    0.54
    VERY
    0.53
    很高
    0.52
    very
    0.51
    Act Density 0.183%

    No Known Activations