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

    Neuronpedia

    INDEX
    Explanations

    expressions of uncertainty and likelihood

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    seitig
    -0.56
     Préférences
    -0.49
     तह
    -0.47
     lisää
    -0.47
    F
    -0.46
    R
    -0.44
    V
    -0.41
     
    -0.41
      
    -0.41
    ことができました
    -0.40
    POSITIVE LOGITS
     likely
    1.53
    likely
    1.47
    Likely
    1.47
     Likely
    1.47
     Probably
    1.42
     probably
    1.40
    probably
    1.38
    Probably
    1.37
     probable
    1.29
     prolly
    1.29
    Act Density 0.406%

    No Known Activations