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

    Neuronpedia

    INDEX
    Explanations

    monetary or financial-related symbols and terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pleaſure
    -0.84
     purpoſe
    -0.82
     itſelf
    -0.79
     fubject
    -0.78
    ſelf
    -0.76
     houſe
    -0.74
    ########.
    -0.71
     ſtate
    -0.71
    ſelves
    -0.70
     ſhall
    -0.68
    POSITIVE LOGITS
    Personendaten
    0.37
     Italijani
    0.37
    Angeb
    0.36
    intios
    0.35
    EndContext
    0.33
     shuts
    0.31
     تعدى
    0.30
     hangs
    0.29
     мәкал
    0.29
    imbawa
    0.29
    Act Density 1.190%

    No Known Activations