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

    Neuronpedia

    INDEX
    Explanations

    references to position in a data structure or coordinate system

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aarrggbb
    -0.80
     GenerationType
    -0.80
    UnsafeEnabled
    -0.79
     itſelf
    -0.78
     pleaf
    -0.77
    COUVER
    -0.77
    PerformLayout
    -0.77
     raiſ
    -0.77
    MessageOf
    -0.77
    󠁴
    -0.76
    POSITIVE LOGITS
    Posted
    0.78
     Posted
    0.70
     accidentes
    0.64
    pos
    0.58
     incidence
    0.55
     '
    0.47
     bằng
    0.44
     muertes
    0.43
     Earlier
    0.43
     Ingenie
    0.43
    Act Density 0.134%

    No Known Activations