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

    Neuronpedia

    INDEX
    Explanations

    modal verbs indicating future actions or possibilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ProtoMessage
    -0.51
    thenReturn
    -0.50
    anine
    -0.48
      
    -0.48
    كرت
    -0.47
     consisting
    -0.47
    oirs
    -0.46
    ese
    -0.45
    Appellant
    -0.45
     amikor
    -0.45
    POSITIVE LOGITS
    testens
    0.79
    ollectionView
    0.77
    tableFuture
    0.76
    future
    0.70
     Nusa
    0.66
     kaarangay
    0.66
     mãi
    0.63
    Geplaatst
    0.61
    alnız
    0.61
    WILL
    0.60
    Act Density 0.360%

    No Known Activations