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

    Neuronpedia

    INDEX
    Explanations

    phrases related to significant events or conclusions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    protos
    -0.56
     gynnwys
    -0.51
    Datuak
    -0.50
    iram
    -0.50
    irection
    -0.50
     czę
    -0.49
    ischer
    -0.48
     ujednoznacz
    -0.48
    leece
    -0.48
     autrement
    -0.48
    POSITIVE LOGITS
     final
    1.16
     last
    1.13
    最後
    1.05
     terakhir
    1.04
    Last
    1.03
     último
    1.01
    最后的
    1.01
     Dernière
    1.00
    last
    1.00
     Last
    1.00
    Act Density 0.209%

    No Known Activations