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

    Neuronpedia

    INDEX
    Explanations

    probable outcomes or assertions throughout the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Z
    -0.51
     miten
    -0.50
     Ches
    -0.49
     movimentos
    -0.49
    CHM
    -0.49
     resultSet
    -0.48
     élevées
    -0.48
    inander
    -0.48
     dance
    -0.48
    orme
    -0.47
    POSITIVE LOGITS
     Probably
    1.48
     probably
    1.44
    Probably
    1.33
    bably
    1.32
     prolly
    1.32
    probably
    1.28
     likely
    1.18
     perhaps
    1.12
     Likely
    1.12
     Perhaps
    1.05
    Act Density 0.090%

    No Known Activations